Vollna AI Bot for Upwork Projects

Below is a brief dot point summary of what we are looking for. Simply, we want to convert our coaching method and philosophy into the digital space and make it accessible for every cricketer around the world.

• Mobile-first, fully accessible platform.
• Secure user accounts including sign-up, login and account management.
• Support for free access, trials, and future paid tiers.
• Flexible payment handling.
• Built-in support for multiple languages and regional language variations.
• A conversational, question and answer experience where users can ask questions naturally and receive responses.
• Ability to maintain context across conversations and support follow-up questions.
• Responses and feedback grounded in our internal coaching framework.
• Capability for users to upload images and videos for feedback.
• Store user information to build personalisation over time.
• Ability to track what users have worked on, including focus areas, drills used and simple reflections over time.
• Strong control over tone and language, aligned with our values and coaching philosophy.
• Consistent response structure that combines explanation, guidance and suggested actions.
• Optional use of images or short videos to support learning.
• Voice functionality allowing users to speak and receive spoken responses.
• Scalable architecture that can grow with more users.
• Internal analytics and insights to understand usage patterns

I’m looking for an experienced AI developer to build an AI-powered calling agent for my laundry business. The goal is to automate inbound and outbound phone calls to handle customer interactions efficiently while maintaining a natural, human-like conversation flow.

This AI calling agent will serve as a virtual receptionist and sales assistant for the business.

Create email, WhatsApp, and call automations in GoHighLevel. The setup should include UTM tracking and other tracking statistics. The automation will last 30 days with 4 touch points per week per client. Experience with GoHighLevel is essential. All touch points need to be measured.
The Automation will be for nurturing prospects, so we will want the data to be filtered into buckets as it goes through the funnel.

• How long have you been using GHL automations?
• How many years have you been using GHL?
• Describe your recent experience with similar projects
• How do you use metrics to inform your strategy?

You will be setting up AI chat Bots for new and excisting clients

We are building an AI-powered phone receptionist system for medical facilities to automate incoming calls when staff are unavailable (after-hours, lunch breaks, weekends, overflow).

The AI voice agent will handle common front-desk tasks like answering patient questions, booking appointments, rescheduling, cancellations, and collecting intake details — while routing urgent calls to humans when needed.

We are looking for an experienced n8n automation builder who can design and implement the backend workflows that power this system.

What the AI Receptionist Must Handle

The voice agent should be able to:

Answer FAQs (hours, location, directions, insurance accepted, services)

Book new appointments

Reschedule or cancel existing appointments

Collect new patient information (name, DOB, reason for visit, contact info)

Escalate urgent or complex calls to a staff member

Log call summaries and patient details into our system

Your Role (n8n + Automation Focus)

You will be responsible for building workflow automations that connect the voice AI agent to real clinic operations, including:

✅ Designing conversation-triggered workflows in n8n
✅ Building webhook integrations between voice platform + backend tools
✅ Automating scheduling and intake pipelines
✅ Storing patient data securely (HIPAA-conscious design)
✅ Creating reusable workflows we can deploy for multiple clinics

Tools & Platforms (Preferred Experience)

We are primarily looking for someone strong in:

n8n automation + workflow design

Webhooks, API integrations, and backend logic

Voice AI platforms such as:

VAPI, Twilio Voice, Retell, Bland, Air.ai, etc.

LLM integration (OpenAI / GPT-based agents)

Bonus experience:

Healthcare or medical front-desk workflow automation

Appointment scheduling software integrations

HIPAA-safe design practices

Deliverables

A working automation backend for one AI receptionist prototype

Appointment + intake workflows connected end-to-end

Configurable workflow templates that can be reused for future clinics

Documentation + handoff for scaling deployments

Ideal Freelancer

✅ Strong n8n builder with real automation portfolio
✅ Understands how to connect voice agents to business operations
✅ Comfortable working with API-driven systems and scheduling workflows
✅ Professional experience with healthcare workflows is a plus

To Apply, Please Include

Examples of n8n workflows or automations you've built

Any experience with voice AI or conversational agents

How you would structure scheduling + intake automation for clinics

Estimated timeline to build a functional MVP

✅ Optional Line to Attract Higher Talent

(Highly recommended)

We are building this as a scalable AI agency offer and are looking for a long-term partner as we deploy across multiple medical facilities.

**Role:** AI Automation Specialist / Notion Architect
**Experience Level:** Expert
**Project Type:** Long-term, Iterative Development

### **The Vision**

I am looking for a long-term partner to help me build a true "Second Brain" in Notion. I don't just want a database; I want an intelligent system that ingests my daily interactions, processes them via AI, and provides actionable insights, strategic alignment, and deep relationship intelligence.

I have a preliminary automation draft in place, but I need an expert to refine, rebuild, and scale this architecture.

### **Phase 1: The Meeting Intelligence Engine**

The first deliverable is a robust system to process meeting data. We want to capture high-fidelity data from meetings without being intrusive.

**The Workflow:**

1. **Audio Capture (Strict Constraint):**
* **NO Zoom/Teams Bots.** We do not want an AI bot joining the call.
* The solution must process audio captured directly from device system audio (Mac) AND via upload (e.g., iPhone voice memos from in-person meetings). (As I take both in person and Zoom Meetings.)
* *Privacy Note:* Transcripts can be deleted after analysis; only the insights need to be stored.


2. **Intelligent Processing (The "Brain"):**
* Transcribe audio (Whisper or similar).
* Generate a detailed yet concise summary using LLMs (Open to your thoughts on which LLMs)
* Extract **Action Items** and populate a dedicated Notion task database (database built).
* **Auto-Tagging:** AI should analyze the context and suggest relationships to existing Projects, Topics, and Areas in Notion.


3. **Contextual Syncing:**
* Cross-reference the recording timestamp with my Calendar.
* Identify attendees automatically based on the invite.
* Pull context from the invite (attachments, agendas) to inform the AI analysis.



### **Phase 2: The "People Intelligence" Layer (CRM)**

This is where the project gets exciting. I want to build a dynamic "Person Database" in Notion that evolves over time. (Person Database already built)

* **Sentiment & Personality Analysis:** The AI should analyze the conversation to gauge the attendee's temperament, goals, values, and communication style.
* **Profile Building:** Automatically update their Notion profile with these insights.
* **Pre-Meeting Briefs:** Use this historical data to prepare me for *future* meetings (e.g., "Last time X was frustrated about Y; approach this topic carefully" or "They value directness").

### **Phase 3: Strategic Alignment & Reporting**

* **OKR Cross-Referencing:** The AI should check meeting topics against my defined Business OKRs and Strategy documents to ensure time is being spent on priorities.
* **Daily Executive Brief:** An end-of-day digest summarizing all meetings, key decisions, and immediate actions.

### **The Ideal Candidate**

* **Deep expertise in Automation Platforms:** ([Make.com preferred, or n8n).
* **Notion Mastery:** You understand relations, rollups, and database architecture, not just basic pages.
* **AI Implementation:** You know how to prompt engineer for specific outputs (JSON formatting, sentiment analysis, summarization).
* **Audio Handling:** Experience handling audio files, splitting large files for API limits, and transcription workflows.

### **To Apply**

Please start your proposal with the word "Brain" so I know you read this. Tell me:

1. How you would handle the "No Bot" audio capture requirement?
2. Your favorite automation you’ve built involving Notion and AI.
3. Your thoughts on how to structure the "People Intelligence" database.

• 1. How you would handle the "No Bot" audio capture requirement?
• 2. Your favorite automation you’ve built involving Notion and AI.
• 3. Your thoughts on how to structure the "People Intelligence" database.

Hi,

We're looking for a knowledge and retrieval systems expert who wants to come help build the next generation of financial retrieval services.

We have a best-in-class AI platform designed for the real estate and mortgage industries. We're looking to really iterate on our knowledge-based system and go from V1 to V2, which is more or less a complete rewrite.

The person or persons or team that we're looking for has expertise in both TypeScript and Python, and bonus points for Go and has experience deploying large-scale backend systems on either AWS or CloudFlare.

• What timezone are you in?
• Who will we be working with, you or a team?
• Give us live + deployed examples of large scale knowledge systems you've built.
• What languages and technical stack are you most proficient in? Name specific libraries as well.

We’re looking for an experienced AI / automation engineer to take over and further develop an existing production AI chatbot used in customer support.

Important context upfront:
We already have a working AI bot, custom-built for our support operations. Unfortunately, the original developer is no longer responsive.

The system works, but iteration and learning have stalled, so we’re looking for someone who can understand the current setup, improve it, and take ownership going forward.

Current setup

• Customer support platform: Gorgias
• AI integration: Draft responses via Gorgias API
• Automation layer: Self-hosted n8n
• Hosting: DigitalOcean droplet
• LLM provider: Gemini (latest model) via OpenRouter
• Data sources:
• SQL database (historical outgoing support emails)
• Shopify data
• Internal structured support data

The AI currently:
• Generates draft replies inside Gorgias for human agents
• Performs database checks before responding
• Uses Shopify + internal data for contextual, order-aware replies

This is not a greenfield project and not a simple FAQ bot, it’s already live and used daily.

What’s not working well (yet)
• The learning loop is slow / appears to be stagnating
• The bot is intended to learn from:
• historical outgoing emails (stored in SQL)
• agent behavior
• That improvement pipeline exists conceptually, but isn’t delivering the expected results
• We were in the process of implementing agent feedback prompting, e.g.:
“No — rewrite this differently”
so the AI can adapt tone, structure, or reasoning over time

At the moment, that adaptive behavior is underdeveloped.

What we’re looking for

Ideally, you:
• Can analyze and improve an existing n8n-based AI architecture
• Are comfortable with:
• LLMs (Gemini, GPT, Claude, etc.)
• Prompt design & iteration
• Feedback loops and evaluation
• Understand when to use:
• prompt engineering
• RAG / vector databases
• structured memory vs fine-tuning
• Can reason about why an AI isn’t learning effectively
• Have opinions on:
• self-hosted n8n vs alternatives
• OpenRouter vs direct providers
• cost / latency / quality trade-offs

We’re very open to architectural recommendations, but we prefer to build on what exists unless there’s a strong, well-argued reason not to.

Bonus points if you:
• Have built customer support AI (Gorgias, Zendesk, Intercom, etc.)
• Have production experience with multi-LLM setups
• Care about cost efficiency and observability
• Can explain complex trade-offs clearly (no buzzword soup)

How to apply:

To confirm you’ve actually read this:
1. Start your message with:
“AI chatbot legend”
2. Briefly describe 1–3 comparable projects
3. If possible, share:
• A live chatbot we can test
• Or a product / website where your AI is actively used

Links and demos are very welcome.

Practicalities
• Freelance / contract role
• Potential for long-term collaboration
• Direct access to:
• n8n workflows
• server & logs
• Gorgias setup
• We value ownership, clarity, and good reasoning over speed

Looking very much forward to your application!

I run a lifestyle business and I'm constantly creating promotions. Right now, I waste hours writing the same promotional content for different platforms - newsletter, Instagram, Facebook, etc. I want to automate this.

My dream: I fill out a simple form/sheets with bullet points about my promotion, and get polished, ready-to-post content for all my marketing channels, and also adapted for different regions.

Important: Sometimes we only have offers in certain regions. Like maybe just UK and NZ, but not US or Asia. The system needs to be smart enough to only create content for regions where I actually have an offer.

jan23 Developing and testing autoscaling python AWS RAG lambda and S3 React Chatbot


Summary
PROJECT TITLE: Build AWS Hosted RAG Chatbot Using LangChain, RDS PostgreSQL with pgvector, lambda Autoscaling, and React UI hosted on S3 AWS and AWS waf and getway api for requests as users access API interface

some help
https://github.com/ed-donner/production/tree/main/week2
https://github.com/AIbyKJ/RAG_chatbot

lambda based aws rag chatbot design : frontend with S3 React, for backend lambda with python code of chatbot using langchain. aws db rds aurora sql postgress for embeddings and chunks and conversation history. lambda is stateless. python packages upload to lambda through docker file (not zip ) since python packages size maybe big (docker created on EC2 and then save to s3. lambda reads docker from s3)

do not forget that test for autoscaling proves that there is no lost requests and that as more users as more aws resources allocated or vice versa as less users as less aws resources allocated

no one resource has public access like ec2 or db (for testing users has backend access using fastapi only through httpS (not http) request with password and or current session token ). All communications inside aws.

main ideas

• Python code and AWS deployment: Backend (FastAPI) and frontend (React) are deployed on AWS and are reachable from any desktop computer and any mobile.
• Core RAG works end-to-end: Users can upload documents, content is embedded into RDS PostgreSQL + pgvector, relevant chunks are retrieved, and answers are generated via OpenAI; chat history is stored and used for retrieval with an option to forget old history.
• Multi-user + security: Admin/user authentication works; role-based access control is enforced; private vs public documents are respected; sensitive resources (DB/S3) are not publicly exposed.
• Autoscaling validated: Load test proves scaling from 0 to 120 concurrent users within 10 seconds with no lost requests (for backend and UI where applicable).
• Reproducible educational deliverables: A step-by-step .doc with screenshots for each step plus an end-to-end video enables you to recreate the full system in your AWS account (AWS Console-first so all development from AWS browser but not from local computer , no terraform or .sh).
• Local Windows tooling: Python client + load-test scripts and instructions run from local Windows to test both backend and front end.
• Full cleanup guide: Clear steps to remove all AWS resources after deployment/testing are provided.
separate material to teach me how to use react for this task
python testing code and architecture to run many queries from my windows local computer to prove it can be done as many as 120 users using app on parallel with autoscaling . from 0 to 120 users and 120 to 0 users during 10 seconds
Details are :
important
do not forget to teach me how to remove all resources after deployment or stop


important
user can access both backend (fast api ) and frontend (React ) from local computer and mobile phone

I do not know REACT so you will create separate material to teach me how to use react for this task : create architecture , code , how to change if needed. Provide both instructional video and .doc file with screen copies and explanations , and react code and how to use vibe coding for such react task. How to test such ui automatically for autoscaling testing

important all deployment should be done from AWS console (no terraform or etc ) , rds access (review , add, change records ), etc. NO use of local computer for aws setups , use local comp only for browsing aws console

defend solution from hackers, like do not provide access to DB to everyone with URL, etc

Overview
I need an experienced developer who understands Python, LangChain, and AWS to build a complete RAG chatbot system. The system must support:
1 multiple users at the same time
2 autoscaling quickly
3 store vector embeddings in Amazon RDS PostgreSQL with pgvector
3 run a clean React user interface.
4 Use OpenAI as LLM, find openai model which can support such load (so many request per minute ) by using usual subscription (not special very expensive ) .
5 Data for RAG : 5 pdf files for each user (general format pdf file for example with pictures and tables , but only textual data should be used including content from tables ), each file has 3 pages (you provide these files). both user and admin can upload pdf files , some files for public use some files only for one user , privet. You provide such synthetic pdf files as many as needed. each user upload it own files
6 users conversation history saved on RDS to use RAG of answers recent history and most suitable historical chunks from previous conversation. Relevance of chunks calculated by taking to account chunks recency as well, add capability to forget too old conversation texts
7 deploy on S3 react and lambda backend .
Make sure when there is no chatbot use (no users using chatbot ) then there is no AWS resources use (no one VM running, then no need to pay to AWS ). When user start conversation when there is no conversation at all , then resources are allocated .
8 it should be the same deployment but supports both backend and frontend request from users from local computer . it needs to test autoscaling for both frontend plus backend and only backend : one for both frontend and backend and one for only backend .

This project includes backend development, database setup, React UI, AWS infrastructure, and load testing.

SYSTEM ARCHITECTURE REQUIREMENTS

Vector Database (Managed)

Use Amazon RDS PostgreSQL

Enable pgvector extension

Store embeddings, metadata, document chunks, users, and admin data

Must be fully managed by AWS (no set up from local comp)

stateless Python Backend (backend can be used not only by aws based React, but also from local windows computer python code, you provide this code to use backend from windows and instructions how to do it , for example needed python packages installation , etc )

Use LangChain for embeddings, text splitting, retrieval, and RAG logic

Backend must be completely stateless
No local file storage
All files go to RDS or S3
Safe for autoscaling LAMBDA instances

AWS Deployment

Use LAMBDA Auto Scaling
Minimum size 1
Maximum size 120 or more

Must be able to scale up within about 5 seconds from 1 to 120 users



Use S3 for file uploads

Set up all IAM roles, security groups, VPC networking, and private subnets

React Web UI
The user interface must include the following:

Admin Panel

Admin login with username and password

Admin dashboard

View users

Reset user passwords

Upload files to the knowledge base

View basic system information

User Panel

User login

Upload personal documents

Ask questions to the chatbot

See chat history

Access control by user role

UI should be clean, simple, and responsive.

RAG CHATBOT FUNCTIONS

Core functions

Upload PDF, DOCX, or TXT files

Automatically split, embed, and store in PostgreSQL

Perform similarity search using pgvector

Retrieve top results for each query

Combine retrieved context with the LLM for answers

Support many users at the same time

Authentication

Admin login

User login

Password hashing

Store all accounts in RDS

Scalability Requirements

Must handle a quick spike in traffic

Example: from one user to twenty users very fast several seconds

Stateless application nodes

Load balanced

Health checks and automatic recovery

LOAD TESTING AND SIMULATION

The project must include tools or scripts that simulate many users using RAG running on AWS from local windows
plain python load test code running on local windows

The simulation must:

provide framework and python code for running form my local windows . Test 120 or more users logging in and use app in parallel . load changing from 0 to high during given time range for example 10 seconds. prove all works correctly , no lost requests for both backed (python ) and frontend ( React )

Upload test files

Send many chatbot messages

Trigger autoscaling

Measure response times and performance

A short report must be included with the results.

DELIVERABLES

Fully working RAG chatbot system

Hosted on AWS

Using RDS PostgreSQL with pgvector

Python backend

React frontend

Auto Scaling infrastructure

Complete codebase

Clean and well structured

Python and react code provided , including how install on local comp for local testing first

Requirements file

Deployment instructions

Full deployment guide

Important Step by step instructions to recreate the system : doc file with instructions with screen copies for each step (especially how and what aws parameters to use) and end to end video with all steps

RDS setup

IAM roles

VPC configuration

Auto Scaling Group setup

React deployment

Database schema

Environment variables

Load testing suite

Scripts for simulating many users

Instructions to run tests

Performance summary

IDEAL DEVELOPER

Strong experience with Python and LangChain

Experience with RDS PostgreSQL and pgvector

Strong AWS background
LAMBDA, Auto Scaling, VPC, IAM, S3

Experience building React apps

Experience with load testing

Ability to deliver stable production quality code

.

HOW TO APPLY
Please include:
Your relevant experience
Any improvements you recommend for the architecture

4 days to do

make sure I can run firstly python code on my local windows by using aws cli for using aws resources like rds and s3 with line by line execution for debugging ( lambda python code runs locally, then I can use copy past to use this code in lambda ) and code exploration. And after I can run fully on AWS.



Important again : you provide .doc file with step by step instructions with screen copies for each step and video how to do end to end. I should be able to reproduce all on my account by myself by using your instructions


new user can register by himself only using provided unique password in advance
for example : I give to new user passwords abc123 then new user can register without admin by using this password , then user create new unique password to login afterward

for each event like registration , login or each chat entrance log is created and saved to S3


acceptance criteria I can run on my aws account and my local windows
I do not provide aws credentials or openai credentials , you use your own credentials for development. then I will use my own accounts for testing

Create needed Backend interface with admin and users input for id and passwords
Backend interface (only very simple starting point as demo https://github.com/AIbyKJ/RAG_chatbot
)
Admin Menu
user_management_menu

("\n--- User Management ---")
("1. List users")
("2. Add user")
("3. Delete user")
("4. Reset user password")
("0. Back to main menu")


chat_management_menu

("\n--- Chat Management ---")
("1. View user chat history")
("0. Back to main menu")

data_management_menu

("\n--- Data Management ---")
("1. Upload PDF(s)")
("2. Upload all PDFs from folder")
("3. List all PDFs")
("4. Delete PDF(s)")
("5. Delete all public PDFs")
("0. Back to main menu")

vectordb_management_menu

("\n--- VectorDB Management ---")
("1. Ingest all public PDFs")
("2. Ingest PDF by filename (public or specific user)")
("3. Remove PDF data by filename")
("4. Remove PDF data by user")
("5. List available PDF data")
("6. Clear all users' memory")
("7. Clear user memory by user ID")
("0. Back to main menu")

#
("\n=== Admin Main Menu ===")
("1. User Management")
("2. Chat Management")
("3. Data Management")
("4. VectorDB Management")
("0. Exit")

USER menu
("\n=== User Main Menu ===")
("1. Upload PDFs")
("2. Upload all PDFs from folder")
("3. List my PDFs")
("4. Ingest a PDF")
("5. Ingest all my PDFs")
("6. List my ingested PDFs")
("7. Delete a PDF from storage")
("8. Delete all my PDFs from storage")
("9. Remove a PDF from vectordb")
("10. Remove all my PDFs from vectordb")
("0. Exit") less

I'm seeking an experienced developer to help create a user journal for my custom Life Coach Assistant ChatGPT bot. The journal should facilitate user interactions and enhance the coaching experience by tracking progress, setting goals, and providing insightful prompts. The ideal candidate will have a keen understanding of user experience design and the ability to create engaging interfaces. If you're passionate about coaching and technology, I'd love to collaborate with you on this project!

We're looking for a Python backend developerto support a short, well scoped task for a consumer fintech app (MUNY). This is a time-sensitive feature test, not long-term engagement.

Please review the attachment.

• Describe your recent experience with similar projects

We’re building GolfShotIQ™, an AI-powered training platform focused on the mental and decision-making side of golf — not swing mechanics. The product uses realistic, scenario-based simulations to help golfers learn how to think through a shot, manage risk, and improve on-course decision quality.

The platform includes:

Scenario-driven golf situations (pre-shot decisions, conditions, hazards, wind, pin position)

An AI Caddie that provides adaptive guidance and feedback

Post-shot reflection and micro-learning grounded in cognitive learning principles

Skill scoring models (risk management, course strategy, commitment, consistency)

Clean, training-focused UI (web-first, mobile-friendly)

We’re looking for experienced freelancers to support areas such as:

UX/UI design (training-focused, minimal, modern)

Front-end or full-stack development

AI / logic systems (decision trees, scoring models, feedback logic)

Product design support and iteration

This is an early-stage but well-defined product with clear documentation, strong vision, and room for long-term collaboration.

I need an AI bot to run on FreeCash the mobile app that gets you to download apps and compete tasks to make money. I need this AI to work fast and smoothly. Hopefully it is better than me sitting here completely all the apps individually. Please be sure to message for more information if needed

Hey there,

The LLM models like GPT, Claude, Gemini, Perplexity are not able to crawl our website scrapingdog.com. They are receiving bot verification every time. I also added a custom rule in Cloudflare to allow these bots, but it's not working.

We are losing a lot of traffic due to this.

What I Need:

Diagnose what is blocking LLM crawlers (GPT-4, Claude, Gemini, Perplexity) despite custom rules
Configure Cloudflare or wordpress settings to properly allow these AI bot user agents
Verify that the fix works by testing with actual LLM tools
Document the solution so we can maintain it going forward

Required Skills:

Expert knowledge of Cloudflare configuration (WAF, Page Rules, Firewall Rules)
Experience with bot management and user agent filtering
Understanding of how LLM crawlers work (OpenAI, Anthropic, Google, Perplexity bots)
Ability to troubleshoot and test solutions

Deliverables:

Working configuration that allows LLM bots to access the site
Documentation of changes made
Verification screenshots/proof that LLM tools can now access the site
Recommendations for ongoing maintenance

Looking forward to working with someone who can resolve this quickly!

Just like Uber Eats, I need a multiple sellers AI mobile App with the following features:
1. Admin - where someone like I can have overview and control of what's happening.
2. Vendors - multiple sellers. Where vendors can upload their products, get notified of customer orders, update order statuses...
3. Customers phase - where customers can view products, add to cart, checkout, pay, view order statuses...
4. Dispatchers window - this phase is where a Dispatcher/rider gets notified of order created, sees where to pick the order from and accept to pick/deliver.

This app is going to work with location. This means that when a customer logs in, it uses the customer location to showcase shops/products according to proximity. I.e shops/products nearest to you. It's going to have QR code and referral links for referral.

We are building a serious AI-powered SaaS platform (not a prototype) and are looking for a senior technical architect to lead system design and guide long-term scalability.

This role is not for a task-based developer.
We already have a dev team. We need someone who can own architecture, data flow, AI reliability, and production readiness from day one.

Our product includes:

AI / LLM-driven workflows

Real-time user interaction

API integrations

User accounts, billing, and role-based access

High-volume data processing

The goal is to build something that:

Can handle real users and revenue

Is safe, scalable, and maintainable

Does not require a rewrite when we grow

What We Need Help With

You will help us:

Review and refine our system architecture

Design backend, database, and API structure

Advise on AI integration patterns (LLMs, agents, tools)

Ensure security, scalability, and data integrity

Provide technical guidance to our in-house developers

We are specifically looking for someone who has:

Built production SaaS platforms

Worked with AI, LLMs, or automation systems

Designed systems that scaled beyond MVP stage

Experience with AWS, modern backend & cloud architecture

This is a long-term role

We’re not looking for a one-off freelancer.
We’re looking for someone who can become a technical partner as we grow.

We value:

Strategic thinking

Clean architecture

Honest feedback

Production-ready engineering

Ideal Background

8+ years building SaaS or large-scale platforms

AI / LLM / automation experience

Strong backend & cloud architecture knowledge

Comfortable working with founders & product teams

Next Steps

Please share:

2–3 similar systems you’ve architected

Your role in those projects

How you typically approach designing a scalable SaaS

Hi,
I’m looking to hire an experienced developer to build an algo trading platform for the Indian market (NSE – Equity/F&O). The platform should support broker API integration, automated strategy execution, risk management, and a user-friendly UI. Experience with Indian brokers (Angel One, Zerodha, etc.) and Python is preferred.
Please share your relevant experience and samples.
Thanks!
I'd like to invite you to take a look at the job I've posted. Please submit a proposal if you're available and interested.

Ankit S.

• Describe your recent experience with similar projects
• What frameworks have you worked with?

We’re looking for an automation engineer to help build a backend-only, event-driven system using n8n’s native multi-agent capabilities.

The work involves implementing a multi-step processing pipeline that handles file ingestion, structured analysis, controlled LLM usage, and generation of versioned outputs. The emphasis is on clean orchestration, predictable behaviour, and well-defined agent responsibilities.

There is no frontend work. The scope is clearly defined, and detailed documentation will be shared after shortlisting.

This role suits someone comfortable working with n8n, backend workflows, and AI-assisted automation who enjoys building reliable systems rather than demos.

• Based on the description provided (see attachment), what is your rough time estimate (in hours) to deliver a first working end-to-end version?
• Roughly how much would you expect one full processing run to cost (AI tokens, n8n costs, pinecone etc) for ~500 files (~100 MB total)?
• We plan to use milestone-based delivery and payments, tied to specific technical outcomes rather than time spent. Is this acceptable to you?
• What is your proposed cost for delivering this project based on the description provided?

Hello,

I hope this message finds you well. My name is Victoria, and I’m seeking a seasoned AI Prompt Engineer to join our team as a consultant, helping us generate a substantial volume of high-quality content.

Role Responsibilities
- Develop and optimize text-to-image, image-to-video, and video-to-video prompts to achieve best-in-class results
- Integrate and orchestrate multiple generation engines in the backend to meet specific creative objectives
- Slice, stitch, and post-process video assets for seamless final products
- Fine-tune end-to-end workflows to ensure scalable, efficient production

Preferred Experience
- Civitai
- LoRA
- Juggernaut XL
- Deforum Stable Diffusion

Given your background in AI prompt engineering, I would welcome the opportunity to engage you in an initial short-term advisory role, with strong potential to evolve into a longer-term engagement based on project needs and mutual fit.

Could we schedule a 30-minute call next week to discuss scope, deliverables, and your consulting rates? Please let me know your availability at your earliest convenience.

Thank you for considering this opportunity. I look forward to the possibility of working together.

Kind regards,
Victoria Nichols

• Describe your recent experience with similar projects
• Please list any certifications related to this project

I’m looking for an experienced GoHighLevel (GHL) automation specialist who can build a fully automated sales bot + CRM workflow for property seller leads (UK / Scotland).

The system must:

Capture inbound leads

Instantly notify me

Automatically start conversations via SMS / DM / Webchat

Qualify property sellers

Route them into the correct pipeline (cash offer vs open market sale)

Book appointments automatically

Hand off hot leads to a human

This is not a basic CRM setup. I need someone who has already built live, revenue-generating GHL + AI bot systems.

Tech Stack (must-have experience)

GoHighLevel (pipelines, workflows, conversations, calendars, custom fields)

CloseBot (or equivalent AI qualification + booking bot)

SMS setup & compliance (STOP keywords, quiet hours)

Facebook Lead Ads / Webhooks into GHL

Property / real estate lead flows (strongly preferred)