Hey everyone! AI / Full-Stack Engineer focused on shipping production-grade LLM + RAG systems ### What I build: • Reliable RAG pipelines for accurate, grounded search & Q&A • Automated summarization + structured extraction • Domain-specific chat agents that actually work in production • Full end-to-end LLM flows (ingestion → retrieval → generation → deployment) ### Stack I usually work with: • Python / TypeScript • FastAPI / Express • SSE streaming • OpenAI, Anthropic, Gemini, Llama 3/3.1, Mistral family • LangChain / LlamaIndex • chunking strategies, hybrid search, re-ranking • Vector DBs: Pinecone, Qdrant, FAISS, OpenSearch • Infra: Docker/K8s, vLLM, AWS/GCP, proper CI/CD If you're working on RAG, agents, fine-tuning, or scaling LLMs in production and want to bounce ideas / collab / need help debugging something — feel free to ping me. Happy to share war stories or look at your setup Looking forward to chatting!