Python & AI Systems Engineering
AI Agents & Orchestration
Agentic systems that combine model reasoning with explicit application logic and operational controls.
LangGraph state machines, tools, persistence, checkpointing, and human approval
Deterministic workflow stages where possible, with model calls at bounded decision points
Retries, cost controls, observability, failure handling, and API/event boundaries
When I'm a good fit
Best fit when an agent must do real work across tools and systems rather than live inside a chat demo.
I focus on production behavior: explicit interfaces, state and persistence, bounded model calls, reliability, cost, and deployability. I am usually not the best fit for frontend-only work or isolated prompt-writing tasks.