Training vs Inference: Why Production Is the Hard Part - Opening Voices with Steeve Morin of ZML

Épisode de Quentin Adam par Quentin Adam · 11 février 2026 · 23 min

What really separates training a model from running it in production? And why does this difference matter so much at scale?

In this second part of Opening Voices, Quentin Adam, CEO of Clever Cloud, continues the discussion with Steeve Morin, founder and CEO of ZML, to clarify a distinction that is often misunderstood.

Starting from concrete explanations, Steeve walks through what training and inference actually involve from an engineering and industrial perspective:

why training is a one-off research effort, while inference is repeated endlessly

why “more is better” applies to training, but becomes a liability in production

why inference represents the vast majority of compute needs

how cost, reliability and margins reshape technical decisions

why operating systems at scale is fundamentally different from building models

This episode helps understand why the real challenge is no longer creating models, but running them reliably, efficiently and sustainably in production.

Hébergé par Ausha. Visitez ausha.co/politique-de-confidentialite pour plus d'informations.

Autres épisodes de « Quentin Adam »

À propos du podcast

Je discute avec celles et ceux qui construisent le numérique. Je suis Quentin Adam, CEO de Clever Cloud. Et j’essaie de comprendre un truc assez simple en apparence : comment fonctionne réellement l’infrastructure du monde numérique. Cloud, intelligence artificielle, open source, architecture…

Quentin Adam

Épisodes similaires

Tous les épisodes de Quentin Adam · Plus de podcasts Actualités