summary
Staff engineer focused on the infrastructure production LLM systems run on: evaluation harnesses, multi-provider dispatch, rate-limit handling, and guardrails on model output. Twenty years of building software, most of it lately in domains where a confidently wrong answer is worse than no answer.
- A deployed MVP is worth two prototyped.
- Dance like nobody is watching, code like everybody is.
- Today's fashion is tomorrow's legacy.
- Debugging becomes easier if you first admit that you are the problem.
- The best code is no code at all.
beyond code
The rest of the operating system
Photography
I shoot animals, landscapes, people, and street scenes. The camera is how I stay observant.
Fiction
I write AI-themed fiction and short stories when technical writing is not enough.
Podcasts & Games
I have opinions about Final Fantasy, narrative design, and the overlap between games and technology.
capabilities
The stack changes. The throughline doesn't. I'm usually working where backend systems, product delivery, and AI workflows collide.
AI & LLM Systems
Measuring model output, routing it across providers, and trusting none of it by default.
- LLM Evaluation & Judge Grading
- Multi-Provider LLM Dispatch
- Token Budgeting & Rate-Limit Engineering
- Structured Output & Guardrails
- Model Context Protocol (MCP)
- Agent Tooling & Orchestration
Languages
Python on the backend, TypeScript for everything else, SQL wherever the data lives.
- Python
- TypeScript
- SQL
Platforms & Tools
Async services on Kubernetes, databases picked per job, front ends in React or Svelte.
- FastAPI
- Redis
- Postgres
- SQLite
- Kubernetes on Azure
- React & Next.js
- SvelteKit
Leadership
Setting technical direction and standards, then reviewing what ships against them.
- Technical Strategy
- Engineering Standards
- Cross-Team Delivery
- Code Review
- Mentoring
selected work
Things you can open and check.
- proof
cc-dash
TypeScript · Model Context Protocol
- proof
Skillbox
Claude Code · Agent tooling
- proof
Agent Compiler
CLI that embeds agent skills into CLAUDE.md and fails CI when the embedded content drifts.
- proof
Using Git Worktrees to Parallelize AI Agents
Writing
- proof
17 Side Projects I Built With Claude Code in Two Months
Writing
- proof
Programmer's Proverbs
680 stars
I help teams implement AI-enabled product work, sharpen engineering practices, and build systems that survive real usage.
Get in touch →