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.
Principles
Proverb 1 of 5
A deployed MVP is worth two prototyped.
Proverb 2 of 5
Dance like nobody is watching, code like everybody is.
Proverb 3 of 5
Today's fashion is tomorrow's legacy.
Proverb 4 of 5
Debugging becomes easier if you first admit that you are the problem.
Proverb 5 of 5
The best code is no code at all.
The rest of the operating system
I shoot animals, landscapes, people, and street scenes. The camera is how I stay observant.
I write AI-themed fiction and short stories when technical writing is not enough.
I have opinions about Final Fantasy, narrative design, and the overlap between games and technology.
What I work with now
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
- cc-dash TypeScript · Model Context Protocol
- Skillbox Claude Code · Agent tooling
- Agent Compiler CLI that embeds agent skills into CLAUDE.md and fails CI when the embedded content drifts.
- Using Git Worktrees to Parallelize AI Agents Writing
- 17 Side Projects I Built With Claude Code in Two Months Writing
- Programmer's Proverbs 680 stars
Let's build something that survives real usage.
I help teams implement AI-enabled product work, sharpen engineering practices, and build systems that survive real usage.
Get in touch →