The New Stack Podcast Why the CNCF's New Executive Director is Obsessed With Inference
Dec 9, 2025
Jonathan Bryce, the new Executive Director of the Cloud Native Computing Foundation, shares his vision on the future of computing, emphasizing the crucial role of inference over training. He believes cloud-native infrastructure is ideal for scaling AI deployment efficiently. Topics include optimizing Kubernetes for managing GPU workloads and the launch of a Kubernetes AI Conformance Program. Bryce predicts that smaller, task-specific models will enhance performance as agents increase inference demands, laying the groundwork for the biggest workloads in history.
AI Snips
Chapters
Transcript
Episode notes
Hundreds Of Conversations Shaped Priorities
- Jonathan Bryce describes learning from hundreds of conversations with companies across industries since becoming CNCF executive director.
- He cites examples from Michelin's Kubernetes use in tire factories to financial services deploying compliant agents.
Inference Will Define The Next Decade
- Jonathan Bryce argues inference, not training, will define the next decade of computing and is where cloud-native excels.
- Inference requires real-time deployment, security, scaling, and observability that Kubernetes and CNCF projects provide.
From Prototype To Efficient Scale
- Early inference deployments use Ray or KServe on Kubernetes to serve models and handle queries.
- Scaling reveals challenges like maintaining context, shared caches, and GPU efficiency as the next phase.