Hands-On AI Engineering: Code First Guide to Building Production Grade LLM Systems with Python | Accompanied with GitHub Tutorials | Learn about Transformers Foundation Models & ML Pipelines - Brossura

Writers, Machine Learning

Brossura

ISBN 13: 9798252097244

Casa editrice: Independently published, 2026

Riassunto

"All of AI… has a proof-of-concept-to-production gap."
— Andrew Ng, DeepLearning.AI

This gap is why most AI projects never make it past the prototype stage.

Hands-On AI Engineering is a practical, code-first guide that teaches you how to move from simple experiments to reliable, production-grade AI systems without relying on expensive cloud credits or black-box APIs.

This book focuses on the real decisions you face when building AI applications: evaluation strategy, cost control, reliability, guardrails, and deployment trade-offs.

What You’ll Learn

• Training and fine-tuning neural networks with PyTorch
• Parameter-efficient fine-tuning using LoRA and QLoRA on consumer GPUs
• Building 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 deployment

Table of contents

• Chapter I – Python Foundations for AI Engineering
• Chapter II – Deep Learning Fundamentals with PyTorch and TensorFlow
• Chapter III – Understanding the Transformer Architecture
• Chapter IV – Understanding Large Language Models (LLMs)
• Chapter V – Tokenization, Context Windows, and Text Chunking
• Chapter VI – Working with Hugging Face Transformers
• Chapter VII – Building AI Applications with LangChain
• Chapter VIII – Parameter-Efficient Fine-Tuning (PEFT)
• Chapter IX – Retrieval-Augmented Generation (RAG)
• Chapter X – Evaluation, Deployment, and Monitoring in AI Systems
• Chapter XI – Building Your AI Engineering Portfolio

Hands-On AI Engineering gives you the guidance needed to move you from an experiment to a dependable system.

Also includes 6 fully working GitHub projects you can run locally, from basic RAG to evaluated systems, agents with memory, and study tools. These projects mirror modern team workflows and give you something concrete to show in interviews or client work.

Dettagli dell'edizione

• Editore: Independently published
• Data di pubblicazione: 2026
• Lingua: Inglese
• ISBN 13: 9798252097244
• Rilegatura: Copertina flessibile
• Numero di pagine: 159
• Contatto del produttore: Manufactured by Amazon on behalf of the author; https://www.amazon.it/hz/contact-us; ; c/o Amazon Media EU S.à.r.l., 38 Avenue John F. Kennedy; Luxembourg; L-1855; Lussemburgo