Recent advances in Artificial Intelligence (AI) have increased the demand for AI products and lowered the barriers to entry for those wanting to create AI products. The model-as-a-service approach has transformed AI from an in-house discipline to a powerful development tool that anyone can use. Everyone, including those with little or no prior experience in AI, can now leverage AI models to create applications. In this book, author Chip Huyen discusses AI engineering: the process of creating applications with readily available foundation models.

The book begins with an overview of AI engineering, explaining how it differs from traditional machine learning (ML) and discussing the new AI stack. The more AI is used, the more opportunities there are for catastrophic failures and, therefore, the more important evaluation becomes. This book discusses different approaches to evaluating open models, including the rapidly growing approach of AI as a judge. AI application developers will discover how to navigate the AI landscape, including models, datasets, evaluation benchmarks, and the seemingly infinite number of use cases and application patterns.

You will learn a framework for developing an AI application, starting with simple techniques and progressing to more complex methods, and discover how to deploy these applications efficiently. Understand what AI engineering is and how it differs from traditional machine learning engineering. Learn the process of developing an AI application, the challenges at each step, and approaches to address them. Explore various model adaptation techniques, including prompt engineering, RAG, fine-tuning, agents, and dataset engineering, and understand how and why they work.

Examine the bottlenecks for latency and cost when serving foundation models and learn how to overcome them. Choose the right model, dataset, evaluation benchmarks, and metrics for your needs. Chip Huyen works on accelerating data analysis on GPUs at Voltron Data. Previously, she was at Snorkel AI and NVIDIA, founded an AI infrastructure startup, and taught Designing Machine Learning Systems at Stanford. She is the author of the bestselling AI book Designing Machine Learning Systems.

AI Engineering builds upon and is complementary to Designing Machine Learning Systems (O'Reilly).

Pages: 528