Books

Master language models through mathematics, illustrations, and code―and build your own from scratch!

Skip the black-box frameworks. Build a production-grade AI coding agent from scratch in pure Python - cloud or local, tested with pytest, all in a single file.

Everything you really need to know in Machine Learning in a hundred pages.

A clear, illustrated guide to large language models, covering key concepts and practical applications. Ideal for projects, interviews, or personal learning.

A model that crashes is a good day. The dangerous failures return answers — plausible, fluent, and wrong. 100 failures. 63 diagnostic instruments. One rule: inspect what actually happened.

Bestselling book on building LLMs. A practical, project-driven manual for engineers who want to understand how modern language models are built — and where they fail — by writing every layer themselves. From a scalar autograd engine to RLHF to fused specialists, in 36 hands-on projects with deliberate sabotage experiments. Build it. Break it. Measure it.

The book highlights the significance of software in systems engineering and uses AI as a subject matter expert. It presents a comprehensive example that covers SysML modeling, including requirements, use cases, logical/ physical architecture, and parametric simulation. It then continues into software, leveraging AI's code generation capabilities to produce software including microcontroller, UI, and DMBS code. It introduces a variety of personas and agents that can help engineers communicate with AI about systems and software engineering. The book also introduces SysML v2, focusing on the new language model and exploring AI's ability to generate models via code generation. Perhaps most importantly, it provides a straightforward roadmap for hardware/software co-design, accelerated at every step by AI. Whether you're a systems or software engineer, or just interested in how to use AI for engineering, AI Assisted MBSE with SysML will prove to be a valuable guide.

Move beyond individual prompts and engineer the full information environment an AI model receives. Learn to design, test, measure, and govern context for reliable AI workflows.

Learn Claude Code by building real projects. This hands-on companion turns the Claude Code Masterclass workshop into a practical self-paced guide for planning, coding, testing, reviewing, refactoring, and shipping software with AI.

Revised for PyTorch 2.x! In 2019, I published a PyTorch tutorial on Towards Data Science and I was amazed by the reaction from the readers! Their feedback motivated me to write this book to help beginners start their journey into Deep Learning and PyTorch. I hope you enjoy reading this book as much as I enjoy writing it.

A practical guide to product engineering in an AI native era, where building shifts from manual construction to steering tools, editors, and agents. Product Engineering with AI covers platforms, agentic workflows, prompting, code quality, UX, and responsible practices for getting from prototype to production. 

What does it really mean to be an architect in the age of AI? If you are a software architect or stepping into the role of AI architect, this question is already shaping your path. Just as we once moved from monoliths to services and from infrastructure to the cloud, we are now designing for intelligent systems that must be explained and trusted. Dear Software and AI Architect is the guide the industry has been missing. Drawing on two decades of practice, field stories, and lessons learned, it shows you how to navigate ambiguity, balance trade-offs, and build trust that scales. You will gain real-world insight into architecting with both software craftsmanship and AI intelligence, use AI as a partner in your craft, and apply enduring principles, patterns, and practices across teams and enterprises. With 50+ caselets, expert voices, and the Architect’s V-Impact Canvas, this book equips you to lead with clarity, build with context, and thrive in the era of AI engineering.

Unlock the power of AI in your applications with this groundbreaking book on AI-driven application architecture. Discover practical patterns and principles for building intelligent, adaptive, and user-centric software systems that harness the potential of large language models and AI components.

AI can help engineers ship code they cannot explain. This complete, illustrated guide helps engineering managers and CTOs grow judgement alongside that speed, with a six-session mentoring course, reusable exercises, and the business case for junior hiring.

Written for people who never asked to become AI users and now are. Not a tour of the technology, but a practical guide to working with it well — the habits that make good results repeatable, and the judgement to know when to check.