SRE / AI Platform Engineer · on stage

Talks& slides

Slides from the talks I give about SRE, Kubernetes and LLM inference. They run in the browser: → to move forward, O for the overview.

Latest talk About me

01 / Archive

One talk

AWS Community Day 2026

Que el modelo quepa en la GPU no te dice a cuánta gente puedes atender. Lo que importa es cuánta conversación cabe, y eso se calcula.