Hands-On AI Engineering: Code First Guide to Building Production Grade LLM Systems with Python Accompanied with GitHub Tutorials Learn about Transform

Hands-On AI Engineering covers both the construction of LLM systems and the core challenges modern AI teams face daily: performance limits, reliability, evaluation, and cost control.

Written by 4 practicing AI engineers. Inside you’ll learn how to design, build, and operate LLM systems that run efficiently, scale, and perform under pressure. Using local, open-source tools, without expensive cloud credits or black-box APIs.

What’s included…

• Training and Fine-Tuning Neural Networks with PyTorch. A set framework on how to effectively train and adapt models using PyTorch.
• Parameter-efficient fine-tuning with LoRA and QLoRA, and how these techniques make it practical to customize large models on consumer GPUs.
• Building robust RAG pipelines through smart chunking, hybrid retrieval, intelligent ranking, and faithfulness/grounding mechanisms.
• Proper evaluation methods including rubrics, LLM-as-a-judge, golden datasets, and regression testing for reliable assessment.
• Production realities. Key insights into monitoring, guardrails, cost optimization, and reliable deployment of LLM systems.

Performance 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.