I build the operating layer around AI.

I currently hold a dual role: AI Engineering Lead across BIFROST, ORVIAN, and Polaris, and Head of Frontend Platform for an enterprise product surface. These systems are the current proof, not the boundary: document intelligence, workflow runtimes, and internal AI assistants are all versions of the same problem of making AI useful inside real operations.

My range is broader than the current product surface. I build AI products, retrieval systems, agent runtimes, full-stack platforms, and the harnesses that let Codex, Claude, and human engineers collaborate without turning the codebase into noise.

My bias is toward retrieval quality, context assembly, eval loops, traces, and reliability. Most AI systems do not fail because the model is weak. They fail because the context is messy, the orchestration is vague, the tools are poorly bounded, and nobody defined what good looks like.

I learned to code at nine with a Pascal book and a dictionary missing half its pages. At twelve I copied a hacker website from Geocities so badly I left their HTML comments in the source for six months. When TensorFlow landed, I got pulled into AI. My first chatbot was a disaster: ask about the weather and it tried to sell you insurance.

Before AI I spent years doing full-stack work for banks and retailers. BBVA, Bankinter, PagoFX, El Corte Inglés, Decathlon. Deadlines were real. Compliance was real. Production bugs were expensive.

My day-to-day stack is Python, FastAPI, Next.js, TypeScript, PostgreSQL with pgvector, Supabase, and Redis. OpenAI and Anthropic APIs when they solve the problem. Not as a reflex.

This site is the personal track: employment conversations, writing, open source, and engineering judgment.