Meet Oscar Castillo & Jeffry Hernández - Speakers at KubeCon + CloudNativeCon North America

Why watch

A preview of a KubeCon session where Oscar Castillo and Jeffry Hernández discuss observing LLM inference running on Kubernetes. The talk covers key observability signals including token latency, throughput, GPU saturation, and application traces. Ideal for ML engineers and DevOps practitioners managing LLM deployments in production Kubernetes environments.