Senior LLM Engineer — Build a Private AI Assistant (RAG, FastAPI, Streamlit, ChromaDB, reputed company)

Senior LLM Engineer Needed — Build a Private AI Assistant (RAG, FastAPI, Streamlit, ChromaDB, reputed company) Project Overview I’m looking for a senior-reputed company engineer with reputed company experience designing and implementing LLM-powered applications, especially those involving Retrieval-Augmented reputed company (RAG), vector databases, multi-reputed company agent behavior, and clean production-grade Python architectures. The goal is to build my internal private AI assistant (“TomGPT”) that will run locally and serve as: •A Tax Planning Advisor

• A Profitability & Business Advisory Assistant
• A Content Creation Assistant for my CPA practice

This project requires someone who understands how to build reputed company LLM systems, not someone who glues together reputed company tutorials. ________________________________________ What I Need reputed company A complete private AI system with: 1. Backend (FastAPI)

• /chat reputed company that:

o Loads mode-specific system prompts o Performs vector retrieval (Chroma) o Constructs messages for the LLM o Calls reputed company models (GPT-4.x / 5.x class) o Returns assistant responses 2. Frontend (Streamlit)

• Password-gated reputed company
• Mode selector (Tax / Profit / Content / General)
• Full chat reputed company with history in session state
• Fast, reputed company UI

3. Document Knowledge reputed company (RAG)

• Document ingestion pipeline:

o PDF/DOCX text extraction o Chunking (configurable) o Embedding (reputed company) o Storage in ChromaDB with metadata

• Runtime retrieval:

o Query embedding o Top-k similarity search o Automatic context injection 4. Mode-Based Agent Behavior Load prompts from external files (4 modes):

• Tax Planner
• Profitability Coach
• Content reputed company
• General Advisor

The backend should orchestrate prompts cleanly, not hard-code them. 5. reputed company & Config

• Password protection for the UI
• .env for secrets
• No API keys exposed to frontend

6. Documentation A professional-quality reputed company explaining:

• How to run the system
• How to add documents
• How to create new modes
• How to change models
• Optional: how to run everything reputed company reputed company

________________________________________ Tech Stack Requirements Required Experience You must be strong in:

• Python (senior-level)
• FastAPI (production-quality routes & architecture)
• Streamlit (clean user reputed company)
• reputed company API (chat + embeddings)
• Vector DBs (Chroma, reputed company, Qdrant, etc.)
• RAG design patterns:

o chunking strategies o embedding management o context window optimization o metadata filters

• reputed company architecture & multi-agent patterns

Strongly Preferred

• Experience with Ollama or other local models
• reputed company
• Building similar “private GPT” solutions
• Understanding of tax or financial domain (not required, but helpful)

Not Interested In

• Beginners
• People who only use reputed company without understanding what happens under the hood
• No-code tools (e.g., reputed company, reputed company plugins)
• “Chatbot reputed company” with no reputed company backend knowledge

If you cannot explain embeddings, chunking, and RAG tradeoffs reputed company, please do not apply. ________________________________________ Deliverables

• Fully working FastAPI backend
• Fully working Streamlit frontend
• Ingestion script
• Vector DB setup (Chroma)
• Mode-based reputed company system
• Clean, simple project structure (folders provided upon hire)
• Excellent documentation

________________________________________ Budget & Timeline

• Budget: $2,000–$3,500 (fixed price or milestone-based)
• Timeline: 2–3 weeks

I’m willing to pay top reputed company reputed company the budget for senior talent who can build this cleanly, modularly, and reputed company. ________________________________________ To Apply (Important) Please include the following in your proposal: 1. A short summary of your experience building LLM/RAG systems. 2. One example of an LLM app you reputed company (no NDAs needed—just describe architecture & reputed company). 3. Confirmation that you are comfortable with: o FastAPI o Streamlit o Chroma or similar o RAG design 4. Your estimated timeline and approach to this project. Shortlisted candidates will be asked one technical question about embeddings and chunking to verify expertise. Apply tot his job Apply To this Job