Skip to content

Applied AI Engineering

The definitive textbook for engineers who build, deploy, and lead production-grade AI systems — from first principles to enterprise scale.

10 Volumes 100+ Chapters Production-First Open Source
10
Volumes
100+
Chapters
500+
Code Examples
50+
Labs
200+
Exercises

Course Philosophy

The Applied AI Engineering Manifesto

Understand every abstraction before using it. Build concepts from scratch before reaching for a library. Focus relentlessly on production engineering — not demos. Learn the why, not only the how.

This is not a collection of tutorials. This is a complete engineering textbook that treats AI with the same rigour applied to systems engineering, distributed computing, or compiler design.

Curriculum

Volume 01

Foundations of AI

History, mathematics, linear algebra, calculus, probability, statistics, and information theory.
Volume 02

Python Engineering

Production Python, NumPy, Pandas, data engineering, testing, packaging, and type systems.
Volume 03

Machine Learning

Supervised, unsupervised, and reinforcement learning from mathematical foundations to scikit-learn.
Volume 04

Deep Learning

Neural networks, backpropagation, CNNs, RNNs, LSTMs, optimizers, and regularisation.
Volume 05

Transformers

Attention mechanisms, the Transformer architecture, BERT, GPT, and pre-trained models.
Volume 06

Large Language Models

LLM internals, prompt engineering, fine-tuning, RLHF, alignment, and inference optimisation.
Volume 07

Retrieval-Augmented Generation

Embeddings, vector databases, hybrid search, re-ranking, and advanced RAG architectures.
Volume 08

AI Agents

ReAct, tool use, planning, memory, multi-agent systems, and production agent frameworks.
Volume 09

MLOps

ML pipelines, experiment tracking, model registry, serving, CI/CD, and monitoring.
Volume 10

Enterprise AI

AI strategy, architecture patterns, governance, risk, cost optimisation, and technical leadership.

Learning Path

01
Foundations — Mathematics, probability, information theory. The substrate everything else rests on.
02
Python Engineering — Write production-quality scientific Python before touching any ML library.
03
Machine Learning — Build linear regression from scratch; understand bias-variance before using sklearn.
04
Deep Learning — Implement a neural network in NumPy; then master PyTorch.
05
Transformers — Code multi-head attention from scratch. Understand every matrix multiply.
06
LLMs — How language models are trained, aligned, and deployed at scale.
07
RAG — Build retrieval pipelines; benchmark retrieval quality; serve at production latency.
08
AI Agents — Design, build, and evaluate autonomous AI systems.
09
MLOps — Ship models to production reliably, observe them, and keep them healthy.
10
Enterprise AI — Lead AI initiatives, build governance frameworks, and drive measurable business value.

How to Use This Textbook

Read sequentially from Volume 1 through Volume 10. Complete every exercise and lab before moving to the next chapter. The prerequisite graph is strictly enforced — resist the temptation to skip.

Each chapter is self-contained with a complete index, glossary, and cross-references. Use the search bar to navigate directly to any concept, algorithm, or technique.

If you have a strong background, start at the volume matching your current level. Check prerequisites in the chapter header to confirm readiness.

Each chapter includes learning objectives, exercises, quizzes, and labs. See the Instructor Guide for syllabi suggestions.

Start Here

New to the course? Begin with Volume 1 — Foundations.

Already have ML fundamentals? Jump to Volume 5 — Transformers.

Building LLM applications? Go directly to Volume 7 — RAG.