Python/FastAPI agent work is my core stack: I've built a production multi-agent orchestration layer (LangGraph ContentPipeline, 33 tests), a YAML-driven AI Workflow API with typed context pipelines and condition branching (FastAPI + ARQ, 148 tests), and a GraphRAG system with hybrid BM25+graph-fusion retrieval (63 tests). For eval methodology: the Jorge AI bot ships with a production_e2e_tests.py (806 lines, B8 invariant checks on every agent response). I'm US-based but comfortable with EU remote overlap.

caymanroden@gmail.com | github.com/ChunkyTortoise