KubeCon + CloudNativeCon North America 2026, Salt Lake City

KEYNOTE

Sovereign AI Starts at the Traffic Layer

Cloud native teams spent a decade building traffic infrastructure they control: open source, decentralized, observable, and running on Kubernetes. Then AI arrived. Inference, the most sensitive layer in the stack, became a call to a vendor API. Your cluster is sovereign. Your AI isn't.

You already run what's needed to reclaim that layer. An inference request is plain HTTP, with the model name in the JSON body. The ingress and Gateway API patterns in the cluster today can route and balance that traffic, and apply policy at the boundary. One data plane, instead of a fragmented traffic stack.

This session covers consistent-hashing across GPU backends and model-aware routing from request inspection, with inference staying inside the cluster. Everything runs on HAProxy, the open source, model-agnostic load balancer and ingress controller built for high throughput and low latency. You keep sovereign control of AI traffic with no performance penalty.

Speaker: Andjelko Iharos

DEMO THEATER SESSION

Universal Mesh: One Model for Ingress, Gateway API, and Multi-Cloud

Kubernetes solved connectivity inside the cluster. Everything else was different: legacy VMs, bare metal, partner networks, and multiple clouds each connected and secured traffic on their own terms. Then service meshes added a proxy to every pod.

Universal Mesh does it differently. One connectivity model spans north-south traffic at the edge and east-west traffic between services, with one proxy layer as the gateway to every environment.

We show the pattern in practice. We cover how to keep existing Ingress manifests working, adopt Gateway API incrementally, and manage CRDs from one control plane, then extend the same model east-west with mutual TLS, multi-cloud connectivity, and VM-to-Kubernetes traffic.

Drawing on real-world migrations after the community Ingress-NGINX controller was retired, we show what maps cleanly, what changes, and what improves. You leave with a migration sequence and a reference architecture to apply at home.

Speakers: Jakub Suchy & Hélène Durand