Taking an AI model from a successful demonstration to a production environment introduces a different set of engineering challenges. Teams must manage GPU availability, inference performance, security, networking, observability, and operating costs while keeping infrastructure reliable at scale. Increasingly, they must also account for autonomous agents interacting with these systems.
KubeCon + CloudNativeCon North America 2026, taking place from November 9–12 at the Salt Palace Convention Center in Salt Lake City, Utah, brings together the cloud native community to examine these challenges. Organized by the Cloud Native Computing Foundation (CNCF), the four-day event expects more than 9,000 attendees, with over 400 sessions covering the technologies and practices shaping cloud native development.
Production AI Moves into the Cloud Native Conversation
AI infrastructure is a major focus this year. The AI Inference + Agentic track explores how organizations can run models on Kubernetes, optimize GPU clusters, manage inference workloads, and build agentic systems using emerging open standards such as MCP and A2A.
Platform engineering is another important area. As enterprises scale Kubernetes across teams and environments, internal developer platforms, automation, and infrastructure management become essential to maintaining consistency without slowing development. The program also examines security, networking, storage, and observability, connecting the operational requirements of modern distributed applications.
The event’s co-located programming adds further depth. November 9 features dedicated gatherings for Cloud Native AI and Inference, Agentics, and other specialist communities. Together, these sessions create a practical bridge between AI development and the infrastructure required to operate it reliably.
Also Read: Wolters Kluwer unites AI leaders to shape enterprise innovation
Cloud Native and AI Leaders on the Keynote Stage
The confirmed keynote lineup includes Jaana Dogan, Software Engineer at Google, whose session explores Agent Substrate and the infrastructure required to run agentic workloads on Kubernetes. Viv Keswani, Senior Director of Engineering at Uber, will discuss the open-sourcing of Michelangelo AI, Uber’s Kubernetes-native machine learning platform.
Also featured are Lucy Sweet, Member of Technical Staff at Anthropic, and Warren Barkley, Vice President of Product Management at NVIDIA. Their sessions will examine Kubernetes fundamentals and how open-source collaboration can support the next generation of AI infrastructure.
Explore the full keynote speaker lineup and conference schedule here.
For developers, platform engineers, and enterprise technology leaders, KubeCon + CloudNativeCon North America 2026 offers a closer look at how open-source infrastructure is adapting to AI workloads, distributed systems, and increasingly autonomous applications.
To know more about the event, agenda, and registration, visit the official KubeCon + CloudNativeCon North America website.