Building AI Systems with Python
Description
This book is a practical, end-to-end guide for engineers and practitioners who want to move beyond prototypes and confidently deploy machine learning and large language model solutions in real-world environments.
This book guides through the entire modern machine learning lifecycle. You'll start with foundations using NumPy, Pandas, and PyArrow for data pipelines, then build solid baselines with scikit-learn. From there, you advance into deep learning with PyTorch, transformers, and LLM adaptation techniques such as LoRA and QLoRA. You'll explore diffusion and multimodal models, and learn to build retrieval-augmented generation systems with FAISS and pgvector. Practical chapters cover agents, tool use, evaluation frameworks, observability, and responsible AI practices including privacy, safety, and governance. Finally, you'll master deployment techniques using FastAPI, Ray Serve, TorchServe, and cutting-edge LLM serving engines like vLLM and TGI. Each concept is paired with clear code examples, testing patterns, and operational checklists. Instead of one-off tricks, you'll adopt repeatable workflows: schema-first tooling, reproducible training pipelines, evaluation with golden datasets, and secure production rollouts with monitoring and compliance checkpoints.
In the end, this book helps you build systems that are robust, auditable, and optimized-whether you're deploying your first model or managing complex enterprise workloads. For engineers who want to ship AI confidently and responsibly, this is your practical playbook for the GenAI era.
What you will learn:
Implement modern AI models including transformers, diffusion, multimodal, recommenders, and RL using practical PyTorch examples.
Fine tune and serve LLMs with LoRA/QLoRA, quantization, RAG, tool calling, structured prompts, and robust evaluation techniques.
Design agentic AI systems with memory, planning, safe tool execution, multi agent patterns, and autonomy evaluation frameworks.
Deploy and run production grade AI with MLOps/LLMOps covering serving, performance tuning, monitoring, cost control, compliance, and edge deployments.
Who this book is for:
This book is designed for practicing machine learning and AI engineers, software engineers moving into applied AI, data scientists building production systems, MLOps/LLMOps practitioners, and technical builders who want to go beyond demos and deploy real-world GenAI, LLM, and PyTorch-based systems at scale.
More details
Person
Martin Hander, Ph.D. (LIGS University), is a technology expert, author, and researcher specializing in artificial intelligence, cloud computing, web services and modern data platforms. With more than 15 years of experience in enterprise software engineering, distributed systems, and cloud-native architectures, he has worked across both academic and industry settings, helping organizations build scalable, secure, and future-ready applications.
When not writing or researching, Martin enjoys mentoring developers, exploring emerging artificial intelligence innovations, and contributing to the global tech community.
Content
Part I - Foundations That Ship (with Python).- Chapter 1 - Machine Learning for Builders.- Chapter 2 - Data Engineering for ML.- Chapter 3 - Evaluation, Testing & Measurement.- Chapter 4 - ML Software Engineering.- Chapter 5 - Optimization 101 in PyTorch.- Part II - Modern Architectures (PyTorch-First).- Chapter 6 - Transformers in PyTorch,.- Chapter 7 - Diffusion & Generative Media.- Chapter 8 - Multimodal Learning.- Chapter 9 - Classical Models That Still Deliver.- Chapter 10 - Reinforcement Learning in Practice.- Part III - LLMs & GenAI in Practice.- Chapter 11 - Core Concepts of LLMs.- Chapter 12 - Efficient Model Adaptation.- Chapter 13 - Prompt Engineering That Lasts.- Chapter 14 - Retrieval-Augmented Generation.- Chapter 15 - Tool-Using LLMs.- Chapter 16 - Evaluation & Visibility.- Chapter 17 - Responsible AI Foundations.- Part IV - Agentic AI & Multi-Agent Systems.- Chapters 18-23 - Agent architectures, memory, tools, coordination, safety, evaluation.- Part V - MLOps & LLMOps.- Chapters 24-29 - Experiment tracking, registries, serving, performance, monitoring, compliance.- Part VI - Edge & Enterprise Deployment.- Chapters 30-32 - Edge inference, enterprise integration, security & provenance.- Part VII - Applied Patterns & Production Playbooks.- Chapters 33-38 - Copilots, chat systems, analytics, personalization, autonomous workflows, enterprise RAG.