Senior Python / FastAPI Engineer for Production RAG, LLMOps & Data Platform

We are looking for a senior Python engineer to help build and scale a production-grade AI and data platform. This is not a basic chatbot project. The work includes backend architecture, RAG pipelines, data ingestion, LLM observability, evaluation, async processing, and production deployment. You will work with: - Python and FastAPI - PostgreSQL and pgvector - RAG, embeddings, reranking, and structured outputs - Redis, Celery, queues, and background jobs - OpenAI, Anthropic, or similar LLM providers - Cloud infrastructure, Docker, CI/CD, testing, and monitoring Strong production experience with Python, FastAPI, PostgreSQL, RAG, data pipelines, and LLMOps is required. Nice to have: LangGraph, LangChain, LlamaIndex, Airflow, Dagster, Kafka, AWS, and Kubernetes. Application requirements Please answer all questions: 1. What scope would you propose for the first 4-6 weeks? 2. Share 2-3 relevant projects you personally worked on, including live links or case-study URLs. 3. What was your exact role in those projects? 4. Why should we choose you over other senior Python or AI engineers? 5. What is your hourly rate? 6. How many hours per week are you available? 7. How do you evaluate RAG quality and monitor failures in production? 8. Please include a short Loom video introducing yourself and briefly explaining one production RAG or LLMOps system you built. Applications without a Loom video and relevant project links will not be reviewed.