Field journal ofAntonin Januska
Sta. 04 · About the observer40.0150° N · 105.2705° WElev. 5,328 ft
Portrait of Antonin against greenery
Fig. 2 — field portrait
Observer's record

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.

LinkedInGitHub
Years building
20+
Blogging since
2012
GitHub stars
600+
Margin notes

Principles

  1. A deployed MVP is worth two prototyped.
  2. Dance like nobody is watching, code like everybody is.
  3. Today's fashion is tomorrow's legacy.
  4. Debugging becomes easier if you first admit that you are the problem.
  5. The best code is no code at all.

See the proverbs project →

Off-trail

Beyond Code

The rest of the operating system.

Antonin hiking in Colorado
Fig. 3 — somewhere above Boulder
  1. Photography

    I shoot animals, landscapes, people, and street scenes. The camera is how I stay observant.

  2. Fiction

    I write AI-themed fiction and short stories when technical writing is not enough.

  3. Podcasts & Games

    I have opinions about Final Fantasy, narrative design, and the overlap between games and technology.

Field kit

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.

Kit 1 of 4

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

Kit 2 of 4

Languages

Python on the backend, TypeScript for everything else, SQL wherever the data lives.

  • Python
  • TypeScript
  • SQL

Kit 3 of 4

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

Kit 4 of 4

Leadership

Setting technical direction and standards, then reviewing what ships against them.

  • Technical Strategy
  • Engineering Standards
  • Cross-Team Delivery
  • Code Review
  • Mentoring

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

Get in touch →
Evidence

Selected work

  1. Proof 01

    cc-dash

    TypeScript · Model Context Protocol

  2. Proof 02

    Skillbox

    Claude Code · Agent tooling

  3. Proof 03

    Agent Compiler

    CLI that embeds agent skills into CLAUDE.md and fails CI when the embedded content drifts.

  4. Proof 04

    Using Git Worktrees to Parallelize AI Agents

    Writing

  5. Proof 05

    17 Side Projects I Built With Claude Code in Two Months

    Writing

  6. Proof 06

    Programmer's Proverbs

    680 stars