This book is a meticulously crafted resource that offers a holistic view of the AI engineering landscape. Authored by Ken Huang, a recognized expert in AI and security, this book provides a structured approach to understanding and applying generative AI in the field of AI engineering. It covers a broad spectrum of topics, from setting up a development environment to advanced applications like multimodal AI and secure engineering practices.
Key Features:
- Comprehensive coverage of AI engineering from basics to advanced applications.
- Code snippets, and practical exercises to reinforce learning.
- Insights into secure AI engineering practices and emerging trends.
Book Description:
The book is designed to be illustrative, offering numerous code examples that readers can adapt to their own projects. It emphasizes practical implementation and collaboration, making it an invaluable resource for both novice and experienced AI engineers. Each chapter includes hands-on exercises, questions, and further readings to deepen your understanding.
What You Will Learn:
- The foundational concepts and tools of AI engineering.
- How to set up a development environment and build GenAI application.
- Techniques for prompt engineering, fine-tuning, and developing RAG based applications.
- How to create multimodal AI applications using images, audio, and video.
- The pros and cons of open-source versus commercial LLMs and navigating supply chain issues.
- Best practices for deploying, serving, monitoring, and maintaining AI applications.
- Secure AI engineering practices to protect against model and application-level attacks.
- Insights into emerging trends in generative AI and the evolving roles of AI engineers.
Who This Book Is For:
This book is ideal for AI engineers, data scientists, machine learning practitioners, and anyone interested in leveraging generative AI for application development. Whether you are starting your journey in AI engineering or looking to deepen your expertise, this guide provides the knowledge and tools to succeed in this rapidly evolving field.
Table of Contents:
Chapter 1: Overview of the AI Engineering Landscape
- Rise of AI engineer role, GenAI applications, no code/low code AI, AI agents, app stacks, etc
Chapter 2: Getting Started As An AI Engineer
- Understanding GenAI fundamentals, setting up dev environment, AI tools/platforms, building "Hello World" GenAI app, etc.
Chapter 3: Prompt Engineering for App Development
-Prompt engineering basics, question answering app, function calling, advanced prompting, research assistant, etc
Chapter 4: Building AI Applications with Retrieval Augmented Generation (RAG)
- RAG, LangChain features, LlamaIndex, optimizing vector databases, evaluating RAG, advanced RAG, etc
Chapter 5: Fine-Tuning Large Language Models
- When to fine-tune, data preparation, model evaluation, tools/platforms, etc
Chapter 6: Build Multimodal AI Applications
- Multimodal models, image/audio/video AI apps, Google Gemini, Jina AI, etc
Chapter 7: Open Source vs. Commercial LLMs and Supply Chain Issues
- Hugging Face, commercial LLMs, licensing, supply chain risks, ML BOMs, open vs. close sourced models
Chapter 8: Deploying and Serving Language Models
- Local vs cloud deployment and more
Chapter 9: AI Application Monitoring and Maintenance
-tools and best practices for monitoring
Chapter 10: Secure AI Engineering Practices
-Innovative GenAI based security tools, multi-agent architectures, MLSecOps
Chapter 11: Emerging GenAI Trends and The Future
-LLM-OS, Robotics applications, Future roles of AI Engineers.
