AI Engineering versus Build a Large Language Model (From Scratch).
Both show up on every "best" list. They're not competitors. They're a sequence. Here's which one to read first, and when.
Reviewed by Ashish Sheth · Updated April 2026
Author
Chip Huyen
Sebastian Raschka
Pages
532
368
Published
2025
2024
Publisher
O'Reilly Media
Manning Publications
Level
intermediate
intermediate
Amazon Rating
4.4/5 (899)
4.5/5 (445)
Goodreads Rating
4.4/5 (1,061)
4.6/5 (313)
AI Engineering
Strengths
+ Clear, accessible explanations of complex AI/ML concepts
+ Practical and implementation-focused rather than theoretical
+ Well-researched with extensive references to current literature
+ Excellent for software engineers transitioning into AI development
Caveats
− Inconsistent depth: some topics feel surface-level for experienced practitioners
− Limited practical code examples
− Breadth-first approach means some topics lack deep coverage
Build a Large Language Model (From Scratch)
Strengths
+ Clear, step-by-step pedagogy that breaks down complex concepts into manageable pieces
+ Hands-on coding throughout, you build a working model on your laptop
+ Excellent diagrams and visual explanations alongside code
+ Companion GitHub repo has 91,000+ stars with bonus materials
Caveats
− Limited mathematical depth on why certain architectural choices exist
− Focuses only on GPT-style architecture, no coverage of alternatives
− Requires solid Python and basic ML knowledge to follow along
The verdict
Build a Large Language Model (From Scratch) is the stronger pick overall, but AI Engineering may suit you better if you're a software engineers transitioning into AI.
AI Engineering
Check Price on Amazon →
Build a Large Language Model (From Scratch)
Check Price on Amazon →
Frequently asked
Which is better, AI Engineering or Build a Large Language Model (From Scratch)?
Build a Large Language Model (From Scratch) is the stronger pick overall, but AI Engineering may suit you better if you're a software engineers transitioning into AI.
Is AI Engineering good for beginners?
You need some software engineering experience. It's not a learn-to-code book. But you don't need a PhD in ML either. If you can write Python and understand APIs, you'll follow along.
Do I need a GPU to follow along?
No. The model you build is small enough to train on a regular laptop CPU. That's intentional. The goal is understanding, not training a production model.