About

AI Engineer focused on agentic AI and multi-agent systems that work in production. I build intelligent workflows that combine LLMs with retrieval augmented generation, tool use, structured outputs, and memory so agents can be reliable, cost-aware, and easy to evaluate.

My work includes designing agent frameworks and orchestration pipelines, integrating models with APIs and enterprise knowledge sources, and adding practical guardrails like permissions, policy checks, and human-in-the-loop review when accuracy matters. I am especially interested in turning prompts into repeatable systems using reusable skills, runbooks, and retrieval-based guidance.

I stay active through conferences and meetups, keep up with new frameworks and research, and share practical lessons with other builders. Always open to connecting with people working on applied AI and agent systems.