Machine Learning Engineering on AWS: Build, deploy, and operationalize LLMs, AI agents, and generative AI systems on AWS Joshua Arvin Lat

About this book

Solve machine learning engineering challenges for GenAI-powered systems and AI agents on AWS, and automate LLMOps pipelines using Amazon Bedrock, SageMaker AI, Bedrock AgentCore, and Strands Agents. Key Features • Build and scale AI agents using Amazon Bedrock AgentCore and Strands Agents • Fine-tune, evaluate, and deploy ML models using Amazon SageMaker AI • Automate LLMOps workflows with SageMaker Pipelines Modern AI systems increasingly leverage large language models, retrieval-augmented generation, and AI agents to power generative AI applications in the cloud. As organizations operationalize these systems at scale, there is a growing need for engineers with strong machine learning engineering expertise. To stay ahead in this rapidly evolving field, you need a deep understanding of AI and ML concepts as well as, practical, hands-on experience with the platforms and tools used to build and operate production-grade AI systems. This book is a practical guide that shows you how to use AWS services such as Amazon Bedrock and Amazon SageMaker AI to fine-tune, evaluate, and deploy LLMs and generative AI systems. You'll learn how to develop RAG-powered systems, build and deploy AI agents using Bedrock AgentCore and Strands Agents, evaluate models using LLM-as-a-judge techniques, and automate LLMOps pipelines using SageMaker Pipelines. The book also covers best practices for building scalable, secure, and production-ready GenAI systems. AWS AI hero Joshua Arvin Lat equips you with the skills and practical knowledge to handle a wide variety of ML engineering requirements, helping you design, operationalize, and secure generative AI systems and AI agents on AWS with confidence. For This book is intended for AI engineers, data scientists, machine learning engineers, and technology leaders who want to deepen their understanding of machine learning engineering, generative AI, large language models, retrieval-augmented generation, AI agents, and MLOps on A