About · Boulder, Colorado
Hi, I'm Antonin.
Staff Engineer building AI-backed systems, engineering standards, and the workflows that let teams ship serious software.
Staff engineer focused on the infrastructure production LLM systems run on: evaluation harnesses, multi-provider dispatch, rate-limit handling, and guardrails on model output.
20+Years building
2012Blogging since
600+GitHub stars
01Principles
- 01
A deployed MVP is worth two prototyped.
- 02
Dance like nobody is watching, code like everybody is.
- 03
Today's fashion is tomorrow's legacy.
- 04
Debugging becomes easier if you first admit that you are the problem.
- 05
The best code is no code at all.
02Beyond 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.
03What I work with now
The stack changes. The throughline doesn't. I'm usually working where backend systems, product delivery, and AI workflows collide.
| Group | Skills |
|---|---|
| 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 |
04Selected work
- projectcc-dashDashboard and MCP server for a portfolio whose state lives in markdown.
- projectSkillboxPersonal and utility prompts packaged as Claude Code skills.
- projectAgent CompilerCLI that embeds agent skills into CLAUDE.md and fails CI when the embedded content drifts.
- writingUsing Git Worktrees to Parallelize AI AgentsEach agent gets its own isolated workspace.
- writing17 Side Projects I Built With Claude Code in Two MonthsTUI apps in Rust and Go, browser games, agent tooling.
- projectProgrammer's ProverbsA collection of proverbs from the programmer.
Work with me
I help teams implement AI-enabled product work, sharpen engineering practices, and build systems that survive real usage.