AI Engineering: Building Applications With Foundation Models
By Chip Huyen
Narrator: Edelyn Okano
Language: English
Category: Audiobook - Computer/Internet
Categories: Computer/Internet
Uploader: Goomer
Uploaded At: 2025-09-15 16:05:31
128 kbps mp3 with chapters named as in book, Release Date June 17, 2025, Listening Length 21 hours and 12 minutes
Description
Recent breakthroughs in AI have not only increased demand for AI products, they've also lowered the barriers to entry for those who want to build AI products. The model-as-a-service approach has transformed AI from an esoteric discipline into a powerful development tool that anyone can use. Everyone, including those with minimal or no prior AI experience, can now leverage AI models to build applications. In this book, author Chip Huyen discusses AI engineering: the process of building applications with readily available foundation models.
The book starts with an overview of AI engineering, explaining how it differs from traditional ML engineering and discussing the new AI stack. The more AI is used, the more opportunities there are for catastrophic failures, and therefore, the more important evaluation becomes. This book discusses different approaches to evaluating open-ended models, including the rapidly growing AI-as-a-judge approach.
AI application developers will discover how to navigate the AI landscape, including models, datasets, evaluation benchmarks, and the seemingly infinite number of use cases and application patterns. You'll learn a framework for developing an AI application, starting with simple techniques and progressing toward more sophisticated methods, and discover how to efficiently deploy these applications.
- Understand what AI engineering is and how it differs from traditional machine learning engineering
- Learn the process for developing an AI application, the challenges at each step, and approaches to address them
- Explore various model adaptation techniques, including prompt engineering, RAG, fine-tuning, agents, and dataset engineering, and understand how and why they work
- Examine the bottlenecks for latency and cost when serving foundation models and learn how to overcome them
- Choose the right model, dataset, evaluation benchmarks, and metrics for your needs
Chip Huyen works to accelerate data analytics on GPUs at Voltron Data. Previously, she was with Snorkel AI and NVIDIA, founded an AI infrastructure startup, and taught Machine Learning Systems Design at Stanford. She's the author of the book Designing Machine Learning Systems, an Amazon bestseller in AI.
AI Engineering builds upon and is complementary to Designing Machine Learning Systems (O'Reilly).
01 - Opening Credits
02 - Bonus Material Notice
03 - Disclaimer
04 - Preface
05 - What This Book Is About
06 - What This Book Is Not
07 - Who This Book Is For
08 - Navigating This Book
09 - Using Code Examples
10 - How to Contact Us
11 - Chapter 1. Introduction to Building AI Applications with Foundation Models
12 - The Rise of AI Engineering
13 - From Language Models to Large Language Models
14 - From Large Language Models to Foundation Models
15 - From Foundation Models to AI Engineering
16 - Foundation Model Use Cases
17 - Coding
18 - Image and Video Production
19 - Writing
20 - Education
21 - Conversational Bots
22 - Information Aggregation
23 - Data Organization
24 - Workflow Automation
25 - Planning AI Applications
26 - Use Case Evaluation
27 - Setting Expectations
28 - Milestone Planning
29 - Maintenance
30 - The AI Engineering Stack
31 - Three Layers of the AI Stack
32 - AI Engineering Versus ML Engineering
33 - AI Engineering Versus Full-Stack Engineering
34 - Summary
35 - Chapter 2. Understanding Foundation Models
36 - Training Data
37 - Multilingual Models
38 - Domain-Specific Models
39 - Modeling
40 - Model Architecture
41 - Model Size
42 - Post-Training
43 - Supervised Finetuning
44 - Preference Finetuning
45 - Sampling
46 - Sampling Fundamentals
47 - Sampling Strategies
48 - Test Time Compute
49 - Structured Outputs
50 - The Probabilistic Nature of AI
51 - Summary
52 - Chapter 3. Evaluation Methodology
53 - Challenges of Evaluating Foundation Models
54 - Understanding Language Modeling Metrics
55 - Entropy
56 - Cross Entropy
57 - Bits-per-Character and Bits-per-Byte
58 - Perplexity
59 - Perplexity Interpretation and Use Cases
60 - Exact Evaluation
61 - Functional Correctness
62 - Similarity Measurements Against Reference Data
63 - Introduction to Embedding
64 - AI as a Judge
65 - Why AI as a Judge
66 - How to Use AI as a Judge
67 - Limitations of AI as a Judge
68 - What Models Can Act as Judges
69 - Ranking Models with Comparative Evaluation
70 - Challenges of Comparative Evaluation
71 - The Future of Comparative Evaluation
72 - Summary
73 - Chapter 4. Evaluate AI Systems
74 - Evaluation Criteria
75 - Domain-Specific Capability
76 - Generation Capability
77 - Instruction-Following Capability
78 - Cost and Latency
79 - Model Selection
80 - Model Selection Workflow
81 - Model Build Versus Buy
82 - Navigate Public Benchmarks
83 - Design Your Evaluation Pipeline
84 - Step 1. Evaluate All Components in a System
85 - Step 2. Create an Evaluation Guideline
86 - Step 3. Define Evaluation Methods and Data
87 - Summary
88 - Chapter 5. Prompt Engineering
89 - Introduction to Prompting
90 - In-Context Learning Zero-Shot and Few-Shot
91 - System Prompt and User Prompt
92 - Context Length and Context Efficiency
93 - Prompt Engineering Best Practices
94 - Write Clear and Explicit Instructions
95 - Provide Sufficient Context
96 - Break Complex Tasks into Simpler Subtasks
97 - Give the Model Time to Think
98 - Iterate on Your Prompts
99 - Evaluate Prompt Engineering Tools
100 - Organize and Version Prompts
101 - Defensive Prompt Engineering
102 - Proprietary Prompts and Reverse Prompt Engineering
103 - Jailbreaking and Prompt Injection
104 - Information Extraction
105 - Defenses Against Prompt Attacks
106 - Summary
107 - Chapter 6. RAG and Agents
108 - RAG
109 - RAG Architecture
110 - Retrieval Algorithms
111 - Retrieval Optimization
112 - RAG Beyond Texts
113 - Agents
114 - Agent Overview
115 - Tools
116 - Planning
117 - Agent Failure Modes and Evaluation
118 - Memory
119 - Summary
120 - Chapter 7. Finetuning
121 - Finetuning Overview
122 - When to Finetune
123 - Reasons to Finetune
124 - Reasons Not to Finetune
125 - Finetuning and RAG
126 - Memory Bottlenecks
127 - Backpropagation and Trainable Parameters
128 - Memory Math
129 - Numerical Representations
130 - Quantization
131 - Finetuning Techniques
132 - Parameter-Efficient Finetuning
133 - Model Merging and Multi-Task Finetuning
134 - Finetuning Tactics
135 - Summary
136 - Chapter 8. Dataset Engineering
137 - Data Curation
138 - Data Quality
139 - Data Coverage
140 - Data Quantity
141 - Data Acquisition and Annotation
142 - Data Augmentation and Synthesis
143 - Why Data Synthesis
144 - Traditional Data Synthesis Techniques
145 - AI-Powered Data Synthesis
146 - Model Distillation
147 - Data Processing
148 - Inspect Data
149 - Deduplicate Data
150 - Clean and Filter Data
151 - Format Data
152 - Summary
153 - Chapter 9. Inference Optimization
154 - Understanding Inference Optimization
155 - Inference Overview
156 - Inference Performance Metrics
157 - AI Accelerators
158 - Inference Optimization
159 - Model Optimization
160 - Inference Service Optimization
161 - Summary
162 - Chapter 10. AI Engineering Architecture and User Feedback
163 - AI Engineering Architecture
164 - Step 1. Enhance Context
165 - Step 2. Put in Guardrails
166 - Step 3. Add Model Router and Gateway
167 - Step 4. Reduce Latency with Caches
168 - Step 5. Add Agent Patterns
169 - Monitoring and Observability
170 - AI Pipeline Orchestration
171 - User Feedback
172 - Extracting Conversational Feedback
173 - Fee++-dback Design
174 - Feedback Limitations
175 - Summary
176 - Epilogue
177 - End Credits
AI Engineering.jpg
Other Torrents
by Chip Huyen
narrated by Edelyn Okano
126 kbps m4b with chapters, Release Date June 17, 2025, Listening Length 21 hours and 12 minutes
m4b | AAC | 126k VBR | 21:12:21 | 0 comments
Computer/Internet
1.1 GiB
Goomer
0
274
by Chip Huyen
2025,requested,pdf only
pdf | 1 comment
Education/Textbook, Technology
30.9 MiB
gmcg001
0
120
by Chip Huyen
O'Reilly Media, First Edition, Published December 04, 2024
epub | 1 comment
Computer/Internet
25.4 MiB
BobBobson
0
733