Antonin Januska
Photograph · on loan from the sitterWall text
The infrastructure production LLM systems run on.
Staff engineer focused on the infrastructure production LLM systems run on: evaluation harnesses, multi-provider dispatch, rate-limit handling, and guardrails on model output.
Principles
Five inscriptions from the proverbs project, carved over the door.
- IA deployed MVP is worth two prototyped.
- IIDance like nobody is watching, code like everybody is.
- IIIToday's fashion is tomorrow's legacy.
- IVDebugging becomes easier if you first admit that you are the problem.
- VThe best code is no code at all.
Beyond code
The rest of the operating system
- PhotographyI shoot animals, landscapes, people, and street scenes. The camera is how I stay observant.
- FictionI write AI-themed fiction and short stories when technical writing is not enough.
- Podcasts & GamesI 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.
Case 1
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
Case 2
Languages
Python on the backend, TypeScript for everything else, SQL wherever the data lives.
- Python
- TypeScript
- SQL
Case 3
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
Case 4
Leadership
Setting technical direction and standards, then reviewing what ships against them.
- Technical Strategy
- Engineering Standards
- Cross-Team Delivery
- Code Review
- Mentoring
Selected work
Objects lent to this gallery from the other wings.
| Loan | Work |
|---|---|
| L.01 | cc-dash TypeScript · Model Context Protocol |
| L.02 | Skillbox Claude Code · Agent tooling |
| L.03 | Agent Compiler CLI that embeds agent skills into CLAUDE.md and fails CI when the embedded content drifts. |
| L.04 | Using Git Worktrees to Parallelize AI Agents Writing |
| L.05 | 17 Side Projects I Built With Claude Code in Two Months Writing |
| L.06 | Programmer's Proverbs 680 stars |
Commissions
I help teams implement AI-enabled product work, sharpen engineering practices, and build systems that survive real usage.
Get in touch →