Price comparison
Enter a valid email at checkout. Your ebook download link is sent to the email address you provide — double-check it before completing your order.
30-day money-back guarantee. File issue? We replace it or refund you — no questions asked.
Digital product — no physical item will be shipped
You'll receive a PDF download link by email immediately after checkout.
Can't find the ebook you're looking for?
Send us the book cover image via the live chat on our website and we'll request it for you. Estimated response time: 10 minutes.
AI Engineering: Building Applications with Foundation Models (2025) by Chip Huyen is the definitive practical guide to building production AI systems with large language models and other foundation models. An Amazon #1 Bestseller in Enterprise Applications, this O'Reilly title distills the emerging discipline of AI engineering into a coherent framework for developers, engineering leaders, and product teams moving AI from prototype to production.
Recent breakthroughs in AI have lowered the barriers to building intelligent applications — the model-as-a-service approach has transformed AI from an esoteric research discipline into a practical development toolkit accessible to anyone. In this book, Chip Huyen explains how AI engineering differs from traditional machine learning engineering and walks through the modern AI stack end-to-end.
Topics covered in depth: foundation model fundamentals; the AI engineering stack; evaluation methodology for open-ended models including AI-as-a-judge approaches; prompt engineering techniques and patterns; retrieval-augmented generation (RAG); agentic workflows and tool use; fine-tuning strategies; dataset engineering; inference optimization; latency, cost, and quality trade-offs; deployment architectures; monitoring and observability; user feedback loops; and building defensible AI products.
Ideal for: software engineers transitioning into AI; ML engineers adapting to foundation models; technical leaders evaluating AI strategy; startup founders building AI-native products; data scientists working with LLMs; and anyone building with OpenAI, Anthropic, Google, Meta, or open-source models.
