Engineering the future of Kubernetes for AI at scale
Kubernetes Google Cloud Ai Infrastructure Inference Batch Processing Platform Engineering Container Orchestration Gke Gpu Scheduling Mlops
This session explores how Kubernetes is evolving to support AI agents, inference, and large-scale batch processing workloads. It covers hardware-aware platform design, infrastructure fluidity improvements, and intelligent resource optimization for enterprise AI deployments. Designed for platform engineers, DevOps professionals, and technical architects building AI infrastructure at scale.
Related videos
Keynote: From Platforms to AI Factories. Has Kubernetes Solved It? - Saiyam Pathak
Beyond VLLM: Distributed LLM Inferencing With Llm-d on Kubernetes - Ravindra Patil, Red Hat
What's new for AI on GKE: Training, serving, and agents
Policy-as-Code for LLM Inference: Cost & Security Guardrails - Sakalya Deshpande, SAP Labs
Evolving KServe: The Unified Model Inference Platform for Both Predictive and... F. Spolti & J. Lee
Keynote: Making Kubernetes for AI Optimized and Reproducible - Nathan Taber & Mark Chmarny (ASL)
Keynote: Rules of the Road for Shared GPUs: AI Inference Scheduling at Wa... M. Muralikrishnan (ASL)
Cloud Native Live: Kubernetes v1.36 Release
Orchestrating ML/AI workloads with TPUs on GKE
Keynote: Engineering Population-Scale AI & AI Infrastructure with Cloud Native Tec... Tittu Varghese
Kubernetes Plane Aerodynamics: Breaking the Architectural... Vasu Chandrasekhara & Stefan Schimanski
