About
CTO at Argmin AI. 12 years building ML and GenAI systems, 9 of them leading the teams behind them. I've spent the last few years on the hardest part of shipping AI: knowing whether the output is actually good. At SuperAnnotate I built LLM-as-a-judge evaluation and data-curation pipelines; before that, credit-risk models for banks. Now I'm building Judge Builder at Argmin AI: it lets any team create an evaluator calibrated to their own examples, so it scores AI outputs the way they would, not with a generic metric. Based in Barcelona.
Badges



Maker History
Argmin AI / Cost Optimization for AIReduce AI agent costs by 10x while keeping quality stableMar 2026
🎉
Joined Product HuntMarch 4th, 2026
Forums
View more