About

Job Description I’m looking for an AI Engineer who can build a fast, reliable, and production-ready RAG (Retrieval-Augmented Generation) system using LangChain and integrate automated workflows using n8n. What I Need A complete RAG pipeline (document ingestion, chunking, embeddings, retrieval). Integration with LangChain for prompt orchestration and output formatting. Fast response time — ide ideally under 2 seconds for queries. Setup of a vector database (Chroma, Pinecone, Weaviate, or Qdrant). n8n automation workflows for: Background processing Alerts and notifications Data syncing Scheduled tasks Deliverables Fully working RAG backend (Python preferred). Clean, modular LangChain code structure. n8n workflows configured and documented. Deployment guidance or support. Brief documentation on how to update data or extend the system. Ideal Freelancer Strong experience with RAG systems, LangChain, vector DBs, and LLMs. Comfortable with Python and API integrations. Experience with n8n, automation, and workflow orchestration. Can optimize for spee If you want, I can also prepare: ✅ A shorter version ✅ A more premium version ✅ A milestone breakdown for fixed-price contract