Hands-On AI Engineering is a practical, code-first guide to building production-grade LLM systems.
Written by 4 practicing AI engineers. It focuses on what AI teams deal with every day: performance limits, reliability, evaluation, and cost control.
You'll learn how to design, build, and operate LLM systems that run efficiently, scale responsibly, and perform under pressure without relying on expensive cloud credits or black-box APIs.
What's included:
Training and fine-tuning neural networks with PyTorchParameter-efficient fine-tuning using LoRA and QLoRA on consumer GPUsBuilding robust RAG pipelines (smart chunking, hybrid retrieval, ranking, and faithfulness checks)Proper evaluation methods (rubrics, LLM-as-a-judge, golden datasets, regression testing)Production realities: monitoring, guardrails, cost optimization, and reliable deploymentPerformance add-ons (last chapter)
A companion GitHub repository, carefully sequenced projects you can follow along with and build yourself.
Project 1 - Simple Companion Chat: Basic chatbot built around a single document.Project 2 - Personal Knowledge Q&A: Ask questions over your own files with grounded answers.Project 3 - Checked Q&A System: Compare AI answers against expected results.Project 4 - Conversational Agent: Multi-turn chat with memory and simple tools.Project 5 - Document Summarizer: Controlled summaries with basic quality checks.Project 6 - Chapter Explorer: Turn text into outlines and short quizzes.These projects mirror modern team workflows and give you something concrete to show in interviews or client work.