Worth it? My AI book journey
From blank page to Bestseller
Share what you've built with the LLM Engineer's Handbook
Our bestseller, LLM Engineer’s Handbook, has helped thousands build and deploy their own LLM and RAG systems from scratch.
If you used our book to bring your AI project idea to life, we would love to hear about it!
First, as a writer and educator, I would love to see how Maxime’s and my book helped you in your AI Engineering journey. As we’ve written this book out of passion, that will mean the world to us.
Secondly, Packt is organizing a contest where you share on social media what you’ve built and how the book helped you navigate the spaghetti world of AI.
The first winner will receive $500. The next five spots will earn a free Packt subscription, giving them access to all Packt’s books.
You can submit the post until May 25!
Looking forward to seeing what you've built!
Writing a book felt like a gamble
But looking back, it was one of the best decisions I’ve ever made.
As of today, the LLM Engineer’s Handbook has:
Sold 12,000+ copies
Become an Amazon bestseller
Given me the freedom to build without pressure
When I completely denounced my social life to focus on writing—
I didn’t know if anyone would read it.
I didn’t know if it would open any doors.
I didn’t know if it would be worth the effort.
Fortunately, it all paid off.
The book gave me breathing room to focus, reinvest, and go all-in on what I love:
Content
AI & Software
Building Decoding ML
But the impact went far beyond the numbers...
It gave me the confidence that my content is good
It led to speaking invites at QCon, ODSC, and DataCamp
It connected me to incredible collaborators like
—which sparked our next course on agentsAnd it directly led to my current consulting role (plus many more I’ve had to turn down)
In short: it’s been the catalyst for almost everything I’m building today.
I'm extremely grateful to
for co-authoring this journey and Gebin George for trusting me with the opportunity.TL;DR:
If you’re thinking about writing a book, do it.
You’re not just publishing words...
You’re publishing proof of who you are and what you stand for.
Here’s the problem with most AI books:
They teach the model, not the system.
Which is fine… until you try to deploy that model in production.
That’s where everything breaks:
Your RAG pipeline is duct-taped together
Your eval framework is an afterthought
Your prompts aren’t versioned
Your architecture can’t scale
That’s why
and I wrote the LLM Engineer’s Handbook...We wanted to create a practical guide for AI engineers who build real world AI applications.
This isn’t just another guide...
It's a practical road map for designing and deploying real-world LLM systems.
In the book, we cover:
Efficient fine-tuning workflows
RAG architectures
Evaluation pipelines with LLM-as-judge
Scaling strategies for serving + infra
MLOps + LLMOps patterns baked in
Whether you’re building your first assistant or scaling your 10th RAG app...
This book gives you the mental models and engineering scaffolding to do it right.
Here's the link to get your copy (20% off using our discount code)
Our goal when we began writing
and I had one goal when we began writing our book:Build something useful for real-world AI development.
We were tired of the framework overviews, "cool" demos, and benchmark results.
We wanted to create a practical, battle-tested handbook for LLM engineers who actually ship.
Each of us came in with our obsessions:
Maxime had built a popular GitHub course, splitting the LLM world into two tracks:
LLM Scientist vs. LLM Engineer
His desire was to delve deeper into the Engineer path, focusing on reproducibility, code, and best practices.
I had built the open-source LLM Twin course.
It started as a personal challenge:
Could I build a digital version of myself?
But to make that vision real, I had to get my hands dirty -
Fine-tuning, RAG pipelines, preference alignment, eval frameworks...
and adopting MLOps patterns that hold up in production.
The writing process surfaced all the hard parts of building with LLMs:
Designing a preference-aligned model that doesn't sound like ChatGPT.
Turning RAG into a system, not a one-off script.
Architecting pipelines with LLMOps as their first-class citizen.
We even had to teach an LLM how to sound like us.
(Spoiler: it kept defaulting to formal academic tone - it took serious iteration to fix)
But that’s what made it fun.
There’s no standard playbook for LLM engineering yet.
The space is evolving fast...
Tools, models, and best practices shift every month.
That’s why we didn’t aim to be “definitive.”
We aimed to be practical.
The LLM Engineer’s Handbook gives you a mental model, a codebase, and a full-stack walkthrough of building real LLM applications (from architecture to evaluation).
If you're building your first agentic RAG app or deploying your 10th model...
This book was written for you.