I’ve spent the last 3+ years as a Generative AI Engineer building production RAG pipelines, multi-agent systems, and LLM-serving APIs. I’ve shipped RAG over proprietary document corpora using Milvus, hybrid search, and cross-encoder reranking; deployed LLM pipelines as authenticated FastAPI services; instrumented agent workflows with LangSmith; and built 10+ internal AI assistants and automation workflows in n8n and Make.com. I’m looking for a remote Generative AI / LLM Engineer role where I can own end-to-end AI features—from retrieval and prompt design to agent orchestration, deployment, and observability. What sets me apart is that I combine hands-on retrieval and agent engineering with backend production discipline and daily use of agentic coding tools like Claude Code and Cursor—so I can move quickly from prototype to reliable shipped system.
No skills.