Artificial Intelligence Engineering: Foundational Concepts and Advanced Methods

Complete Table of Contents

Chapters 1–5 · Building the mathematical toolkit every AI engineer needs

Chapter	Title	Pages	Key Topics
1	The Landscape of AI Engineering	~35	AI history, subfields, modern AI stack, career paths
2	Linear Algebra for AI	~35	Vectors, matrices, eigendecomposition, SVD, NumPy
3	Calculus, Optimization, and Automatic Differentiation	~35	Gradients, chain rule, SGD, Adam, autograd
4	Probability, Statistics, and Information Theory	~35	Bayes' theorem, distributions, entropy, KL divergence
5	Python for AI Engineering	~35	NumPy, pandas, matplotlib, Jupyter, profiling

Chapters 6–10 · Classical ML algorithms and the art of modeling

Chapter	Title	Pages	Key Topics
6	Supervised Learning: Regression and Classification	~35	Linear/logistic regression, SVMs, decision trees, ensembles
7	Unsupervised Learning and Dimensionality Reduction	~35	K-means, DBSCAN, PCA, t-SNE, UMAP
8	Model Evaluation, Selection, and Validation	~35	Cross-validation, metrics, bias-variance, hyperparameter tuning
9	Feature Engineering and Data Pipelines	~35	Encoding, scaling, feature selection, sklearn pipelines
10	Probabilistic and Bayesian Methods	~35	Naive Bayes, Bayesian inference, MCMC, probabilistic programming

Chapters 11–17 · From perceptrons to generative models

Chapter	Title	Pages	Key Topics
11	Neural Networks from Scratch	~35	Perceptrons, MLPs, activations, backpropagation, PyTorch basics
12	Training Deep Networks	~35	Loss functions, optimizers, learning rate schedules, batch norm
13	Regularization and Generalization	~35	Dropout, weight decay, data augmentation, early stopping
14	Convolutional Neural Networks	~35	Convolutions, pooling, ResNet, transfer learning for vision
15	Recurrent Neural Networks and Sequence Modeling	~35	RNNs, LSTMs, GRUs, sequence-to-sequence, teacher forcing
16	Autoencoders and Representation Learning	~35	Vanilla AE, VAE, contrastive learning, self-supervised methods
17	Generative Adversarial Networks	~35	GAN training, DCGAN, StyleGAN, evaluation metrics

Chapters 18–25 · The transformer revolution and modern NLP

Chapter	Title	Pages	Key Topics
18	The Attention Mechanism	~35	Bahdanau attention, self-attention, multi-head attention
19	The Transformer Architecture	~35	Encoder-decoder, positional encoding, layer norm, building a transformer
20	Pre-training and Transfer Learning for NLP	~35	Word2Vec, BERT, masked LM, tokenization, HuggingFace
21	Decoder-Only Models and Autoregressive Language Models	~35	GPT architecture, causal masking, text generation, sampling
22	Scaling Laws and Large Language Models	~35	Chinchilla scaling, emergent abilities, model families, benchmarks
23	Prompt Engineering and In-Context Learning	~35	Zero/few-shot, chain-of-thought, structured outputs, evaluation
24	Fine-Tuning Large Language Models	~35	Full fine-tuning, LoRA, QLoRA, PEFT, instruction tuning
25	Alignment: RLHF, DPO, and Beyond	~35	Reward modeling, PPO, DPO, constitutional AI, red teaming

Chapters 26–30 · Vision, audio, video, and multimodal intelligence

Chapter	Title	Pages	Key Topics
26	Vision Transformers and Modern Computer Vision	~35	ViT, DeiT, Swin, object detection, segmentation
27	Diffusion Models and Image Generation	~35	DDPM, score matching, Stable Diffusion, ControlNet
28	Multimodal Models and Vision-Language AI	~35	CLIP, LLaVA, Flamingo, image captioning, VQA
29	Speech, Audio, and Music AI	~35	Whisper, TTS, spectrograms, music generation
30	Video Understanding and Generation	~35	Video transformers, temporal modeling, video generation

Chapters 31–35 · Building, deploying, and scaling AI systems

Chapter	Title	Pages	Key Topics
31	Retrieval-Augmented Generation (RAG)	~35	Embeddings, vector databases, chunking, hybrid search
32	AI Agents and Tool Use	~35	ReAct, function calling, agent frameworks, planning
33	Inference Optimization and Model Serving	~35	Quantization, distillation, KV caching, vLLM, TensorRT
34	MLOps and LLMOps	~35	Experiment tracking, CI/CD for ML, monitoring, evaluation
35	Distributed Training and Scaling	~35	Data parallelism, model parallelism, FSDP, DeepSpeed

Chapters 36–39 · Specialized domains and cross-cutting concerns

Chapter	Title	Pages	Key Topics
36	Reinforcement Learning for AI Engineers	~35	MDPs, Q-learning, policy gradients, PPO, GRPO
37	Graph Neural Networks and Structured Data	~35	GCN, GAT, message passing, molecular graphs
38	Interpretability, Explainability, and Mechanistic Understanding	~35	SHAP, attention visualization, probing, mechanistic interpretability
39	AI Safety, Ethics, and Governance	~35	Bias, fairness, regulation, responsible AI

Chapter 40 · Where AI engineering is headed

Chapter	Title	Pages	Key Topics
40	The Future of AI Engineering	~35	Test-time compute, world models, AGI debates, career evolution

Integrative projects applying concepts across multiple parts

Project	Title	Chapters Applied
1	Build a Production RAG System with Guardrails	20, 23, 31, 32, 33, 34
2	Fine-Tune and Deploy a Domain-Specific LLM	12, 19, 24, 25, 33, 34
3	End-to-End Multimodal AI Application	26, 27, 28, 31, 32, 34

Appendix	Title
A	Mathematical Foundations Reference
B	Statistical Tables and Distributions
C	Python and PyTorch Quick Reference
D	Datasets and Data Sources
E	Glossary
F	Notation Guide
G	Answers to Selected Exercises
H	Bibliography