AI Developer - LLM, Vector DB & Reinforcement Learning Expert (FastAPI)

We’re looking for an experienced AI Developer to enhance our existing FastAPI application with advanced AI capabilities. You’ll work with cutting-edge technologies including multiple LLMs, vector databases, and reinforcement learning. What You’ll Work On: Enhance our existing FastAPI-based AI application Implement and optimize vector database solutions for semantic search Integrate multiple LLM models (GPT-4, Claude, and others) with multi-orchestration Build and improve RAG (Retrieval-Augmented Generation) pipelines Implement MCP (Model Context Protocol) integrations Apply reinforcement learning techniques to optimize system performance Design multi-model orchestration workflows Must-Have Skills: Vector Databases (Pinecone, Weaviate, Qdrant, Chroma, or similar) LLM Integration (OpenAI GPT, Claude, and other models) FastAPI framework expertise RAG (Retrieval-Augmented Generation) implementation MCP (Model Context Protocol) Reinforcement Learning practical experience Multi-model orchestration Python (advanced level) Embedding models and semantic search Prompt engineering Nice to Have: LangChain, LlamaIndex, or similar frameworks Model fine-tuning and optimization Docker and cloud platforms (AWS/GCP/Azure) LLM monitoring and observability tools To Apply: Please include: Your experience with LLMs (GPT, Claude, etc.) Examples of RAG systems you’ve built Vector database projects you’ve worked on Any reinforcement learning implementations Your hourly rate or project estimate Important: Only apply if you have proven experience with vector databases, multiple LLM integrations, and RAG systems. Please share relevant portfolio links or GitHub repos.