Professional Overview
Applied AI Engineer who makes LLM agents do economically valuable (and viable) tasks. Following LLM developments since GPT-2 (2019). I specialize in agentic behavioral evals, human validation pipelines, and multi-LLM-as-judge systems. Former Technical PM who scaled a platform to 100k users and led cross-functional agile teams.I write production code with AI tools (Claude Code, Cursor): the LangGraph academic writing & research assistant and RAG+web search microservices I built serve 50k MAU and 100k daily requests.