AI Engineering Roadmap: A Guided Study Companion
Hi, I’m Jean
I’m the Founder and host of Exaltitude on YouTube. I’ve worked in tech for the past 20 years as an engineer, an engineering manager, and a team builder. I was the 19th engineer at WhatsApp and worked with Facebook as an Engineering Manager for six years after the $19B acquisition.
Throughout my career, I’ve mentored and coached countless Software Engineers and Managers from diverse backgrounds, noticing common questions around direction and growth: “Where am I headed, and how do I get there?” This inspired me to share my insights, helping future engineers build purposeful, successful careers.
Stay connected for updates, industry insights, and career advice on LinkedIn and YouTube.
Have questions? Reach out on my website!
About the Book
AI Engineering by Chip Huyen is the most comprehensive modern textbook on building AI systems in production. Unlike most machine learning books that focus on training models, this book explains how to use foundation models to build real-world applications, including prompting, retrieval, agents, finetuning, evaluation, deployment, and system design.
It blends research-level rigor with practical engineering patterns, pulling from more than 1,200+ references across industry and academia. The book introduces a complete mental model for AI engineering as a discipline, shifting the focus from experimentation to shipping and operating AI systems.
This companion guide distills the major topics of the book and pairs them with the canonical papers and resources that matter most, allowing you to study efficiently without having to read everything end-to-end.
How To Use This Guide
This study guide is designed to help you learn AI engineering in a structured and efficient way without getting lost in the 500+ pages and 1,200 citations of the full book. Each section corresponds to a major concept from AI Engineering and includes a brief summary plus the most important reference papers for deeper study.
Use it in three ways:
As a map of what to learn next: Read each section in order to understand how the pieces of AI engineering fit together.
As a filter for what not to read: Instead of drowning in research papers, this guide highlights the relevant papers that shaped the field and are still referenced today.
As a companion while watching or building: Keep this guide open while you work through examples, tutorials, or demos. It tells you why each technique exists and when it should be used in practice.
This guide is not meant to replace Chip Huyen’s book. It is meant to make the book faster to absorb and easier to apply.
Video Companion
Who Is This For?
This study guide is for people who want to work in AI without needing a PhD, a deep math background, or years of machine learning research experience.
AI engineering is a practical, applied field. You don’t need to master calculus or train giant models from scratch to get started. If your goal is to build useful AI products, systems, and workflows, you can learn this path directly.
There are also many AI careers that don’t require coding at all, like:
AI Product Management
AI Strategy Consultant
AI Safety & Policy
AI UX Design
AI User Research
AI Program & Operations Roles
AI Design & Prototyping
AI Recruiting & Talent Roles
For 99% of people entering the AI industry, learning how modern AI systems work and how to use them effectively is far more important than becoming a research scientist.
If you want to break into AI, whether as a builder or as a strategic leader, and you prefer clarity over theory, systems over formulas, and real product skills over academic prerequisites, this guide is for you.
Study Guide
What is AI Engineering?
AI engineering focuses on building real-world applications on top of foundation models rather than training models from scratch. The emphasis is on integrating existing models into functioning systems that solve real problems.
→ Reference: Chapter 1 (AI Engineering)
→ Resource: AI, Machine Learning, Data Science: Which is the Better Career
Understanding Foundation Models
Foundation models are large pretrained models that act as the base layer for downstream AI systems. Understanding how they are trained, aligned, and scaled helps you choose the right model for your use case.
→ Reference: Chapter 2 (AI Engineering)
→ Key Topics:
Training data
Modeling
Post-training
→ Resources:
[Gopher] Scaling Language Models: Methods, Analysis & Insights from Training Gopher (DeepMind, 2021)
Introduced the modern large-scale scaling paradigm and analyzed how performance improves as models grow.
[InstructGPT] Training language models to follow instructions with human feedback (OpenAI, 2022)
Showed how human feedback and preference optimization transformed raw LLMs into helpful assistants.
The Llama 3 Herd of Models (Meta, 2024)
Demonstrated state-of-the-art synthetic data generation and verification strategies used in modern training pipelines.
