Skip to content

whoami

Jonathan Muszkat

Jonathan Muszkat

CTO & Co-Founder at Selenios. Building AI agents for recruiting. Buenos Aires, Argentina.

cat about.txt

I run engineering at Selenios, where we build AI agents that do the recruiting work nobody enjoys: sourcing candidates, screening them over WhatsApp and voice, taking interview notes and turning them into scorecards. Recruiting teams get their time back; candidates get an answer in minutes instead of weeks.

Before that: nearly two decades of shipping software, from founding engineer at a luxury e-commerce marketplace to staff engineer at a workforce platform. I like small teams, boring infrastructure, and finding out what is actually true in production before deciding anything.

I write here about Next.js, AI agents, and the parts of running engineering at a startup that do not make it into the release notes. Full experience →

cat talks-and-mentoring.md

I speak at conferences about putting AI to work inside enterprise environments: what actually ships, what the security and compliance teams will ask, and how to measure whether an agent is doing the job or just producing text. Field notes, not slideware.

I also mentor early-stage startups on technical strategy: choosing what to build versus buy, hiring the first engineers, and keeping a small team fast without setting the infrastructure on fire.

invite me to speak or ask for mentoring →

ls -t blog/

  1. Batch Inference: Same Model, Half the Price, and Production Never Notices

    Every major LLM provider sells a batch mode at 50% off, and most teams still run their bulk work on-demand. How we used it to migrate tens of thousands of CVs at half the cost without touching production, what it charges you in exchange, and the checklist we learned the hard way.

  2. Jev Doesn't Generate. That's the Point: Building a Browser QA Loop on TypeSafe's System One Model

    A model that returns calibrated decisions instead of text landed on Vercel's AI Gateway this week and became its fastest-adopted launch. I built a Playwright QA loop where Jev judges every step, measured it, and compared it to the LLMs you already pay for.

  3. Next.js 16.3 From the CTO Seat: Five Apps, One Month, Three Bugs

    We adopted Next.js 16.3 across five production apps the week it shipped. What paid off, how Cache Components quietly changed our HTTP status codes, and why experimental still means experimental.

  4. Ralph Loop: The AI Development Methodology Taking Over 2026

    Discover the Ralph Wiggum technique—an autonomous AI agent loop that lets Claude Code work continuously until your project is complete.

  5. MCP: The Protocol Connecting AI to Everything

    Exploring Anthropic's Model Context Protocol (MCP) and how it's revolutionizing the way AI models interact with external tools and data sources.

all posts →

./tetris

There is a Game Boy Tetris hidden on this site. Play it, then send me your score.