AI Engineer - Agentic Automation & LLM Integration

We are looking for an experienced AI engineer to help us design and ship production-grade agentic AI systems for clients across multiple industries. The goal is to move beyond simple chatbot wrappers and build tool-using agents that execute real multi-step workflows, integrate with existing business systems, and hand back reliable, structured results. Responsibilities:  Design and build agentic workflows using LangChain - planning, tool-calling, multi-step reasoning.  Build RAG pipelines: chunking, embeddings, retrieval tuning, and grounding outputs in real client data.  Connect agents to existing business systems (CRMs, internal APIs, databases) and automation tools like n8n.  Build the supporting full-stack layer so agents are usable, not just scriptable.  Implement guardrails, logging, and human-in-the-loop approval where accuracy matters. Requirements:  Proven experience shipping production LLM/agent systems  Strong Python, hands-on experience with LangChain or equivalent frameworks, and OpenAI/Anthropic API integration.  Full-stack experience  Practical understanding of RAG architecture and vector databases (pgvector, Pinecone, or similar).  Comfortable working directly with clients When submitting your application, please include examples of live or shipped AI agent/RAG projects, the stack used, and your role in each.