Fix RAG Pipeline for Medical Document Q&A

We are looking for an experienced AI/Backend Engineer to troubleshoot and optimize a partially developed RAG pipeline. The application is built using FastAPI, LangChain, and OpenAI, but is currently producing inaccurate retrieval results. Scope of Work: Review and debug the current vector embedding and retrieval pipeline. Optimize chunk sizing and metadata filtering to improve retrieval accuracy. Update LLM prompts and ensure API endpoints return clean JSON. Test and validate the system to ensure reliable, accurate output. Required Skills: Proven experience with RAG systems, LangChain, and OpenAI APIs. Strong knowledge of FastAPI and backend API development. Ability to quickly identify root causes and implement effective solutions.