Discover Generative AI on Kubernetes by Roland Huß and Daniele Zonca, a practical guide for developers, MLOps engineers, and AI professionals who want to build and scale modern AI systems using Kubernetes.
This book provides a hands-on roadmap for training, fine-tuning, deploying, and managing large language models (LLMs) in cloud-native environments. It explains how Kubernetes has become a key platform for running resource-intensive AI workloads efficiently and at scale.
Readers will learn how to optimize infrastructure, automate workflows, and handle challenges such as GPU resource management, scalability, and system reliability. The book also explores real-world techniques for deploying production-ready AI applications and managing complex GenAI systems.
With practical examples and modern tools, this guide is ideal for software engineers, DevOps professionals, and anyone interested in combining artificial intelligence with cloud-native technologie
