
Hi, I'm Antonin.
Staff Engineer building AI-backed systems, engineering standards, and the workflows that let teams ship serious software.
Credits
Written, engineered and directed byAntonin Januska
Memorable quotes · Principles
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.See the proverbs project →
Department of capabilities · 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 SystemsMeasuring model output, routing it across providers, and trusting none of it by default.LLM Evaluation & Judge GradingMulti-Provider LLM DispatchToken Budgeting & Rate-Limit EngineeringStructured Output & GuardrailsModel Context Protocol (MCP)Agent Tooling & Orchestration
LanguagesPython on the backend, TypeScript for everything else, SQL wherever the data lives.PythonTypeScriptSQL
Platforms & ToolsAsync services on Kubernetes, databases picked per job, front ends in React or Svelte.FastAPIRedisPostgresSQLiteKubernetes on AzureReact & Next.jsSvelteKit
LeadershipSetting technical direction and standards, then reviewing what ships against them.Technical StrategyEngineering StandardsCross-Team DeliveryCode ReviewMentoring
Selected work
TypeScript · Model Context Protocolcc-dash
Claude Code · Agent toolingSkillbox
CLI that embeds agent skills into CLAUDE.md and fails CI when the embedded content driftsAgent Compiler
680 starsProgrammer's Proverbs

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.
I help teams implement AI-enabled product work, sharpen engineering practices, and build systems that survive real usage.
Get in touch →