AntJanusHerbarium · Boulder, Colo.

Tab. V · Descriptio

Antoninus januska

Hi, I'm Antonin.

Staff Engineer building AI-backed systems, engineering standards, and the workflows that let teams ship serious software.

Portrait of Antonin Januska against greenery
Fig. 1 — the collector, in his natural habitat

Diagnosis

In short

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
MensuraeHerb. AntJanus
20+Years building
2012Blogging since
600+GitHub stars

Aphorismi

Principles

Kept the way Linnaeus kept his: short, numbered, and meant to be argued with.

See the proverbs project →

  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.

Antonin hiking in Colorado
Fig. 2 — observed at altitude, Colorado

Beyond 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.

Clavis

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.

Read as a key: each lead describes the work, the name at the end identifies it

  1. 1a.

    Measuring model output, routing it across providers, and trusting none of it by default. . . . . . AI & LLM Systems

    • LLM Evaluation & Judge Grading
    • Multi-Provider LLM Dispatch
    • Token Budgeting & Rate-Limit Engineering
    • Structured Output & Guardrails
    • Model Context Protocol (MCP)
    • Agent Tooling & Orchestration
  2. 2b.

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

    • Python
    • TypeScript
    • SQL
  3. 3a.

    Async services on Kubernetes, databases picked per job, front ends in React or Svelte. . . . . . Platforms & Tools

    • FastAPI
    • Redis
    • Postgres
    • SQLite
    • Kubernetes on Azure
    • React & Next.js
    • SvelteKit
  4. 4b.

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

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

Exsiccatae

Selected work

cc-dashTypeScript · Model Context ProtocolSkillboxClaude Code · Agent toolingAgent CompilerCLI that embeds agent skills into CLAUDE.md and fails CI when the embedded content drifts.Using Git Worktrees to Parallelize AI AgentsWriting17 Side Projects I Built With Claude Code in Two MonthsWritingProgrammer's Proverbs680 stars

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

Get in touch →