Engineering AI Systems: Architecture and DevOps Essentials
Upcoming book. Available for pre-order on Amazon.
AI Engineering is the application of software engineering principles and techniques to the design, development, and operation of AI Systems.
A system that incorporates AI has, roughly speaking, two portions: the AI portion and the non-AI portion. Most of what you will read elsewhere about AI systems focuses on the AI portion and its construction. That is important, but equally important are the non-AI portion and how the two portions are integrated. The quality of the overall system depends on the quality of both portions and their interactions. All of that, in turn, depends on a great many decisions a designer must make, only some of which have to do with the AI model chosen and how it is trained, fine-tuned, tested and deployed.
Accordingly, in this book we focus on the overall system perspective and aim to provide a holistic picture of engineering and operating AI systems – such that you, your SE & AI teams, your company, and your users get good value out of them, with effective management of risks.
The book covers 15 chapters:
1️⃣ Introduction
2️⃣ Software Engineering Background
3️⃣ AI Background
4️⃣ Foundation Models
5️⃣ AI Model Lifecycle (with Boming Xia)
6️⃣ System Lifecycle (with Boming Xia)
7️⃣ Reliability
8️⃣ Performance
9️⃣ Security
🔟 Privacy and Fairness
1️⃣1️⃣ Observability
1️⃣2️⃣ Case Study: Using a Pretrained Language Model for Tendering (with Sven Giesselbach and et. al)
1️⃣3️⃣ Case Study: Chatbots for Small and Medium-Sized Australian Enterprises (with Roozbeh Derakhshan and Cori Stewart)
1️⃣4️⃣ Case Study: Predicting Customer Churn in Banks (with Ming Jian Tang and Andrea Luo)
1️⃣5️⃣ The Future of AI Engineering
One critical aspect of building AI systems is data preparation, which often involves complex data cleaning tasks. As foundation models continue to expand their capabilities, they are increasingly being applied to areas such as data cleaning and preparation. To explore this, we conducted an experiment using ChatGPT (with GPT-4o) to assist in cleaning and analyzing a messy dataset. The results of this experiment highlight the practical applications of AI in system development and data management. A summary of the experiment and its findings is included in this book, with the full dialogue available online.
About the author:
Dr. Len Bass has been an active researcher in software architecture for 30 + years and an active researcher in DevOps for 10+ years. He has been teaching DevOps to graduate students for 7 years. He is an author of a best selling book on software architecture and has written three books on DevOps.
Dr. Qinghua Lu is a principal research scientist at CSIRO’s Data61. She leads the Software Engineering for AI research team and Responsible AI science team at CSIRO’s Data61. She received her PhD from University of New South Wales in 2013. Her current research interests include responsible AI, software engineering for AI, AI safety, and software architecture. She is the winner of the 2023 APAC Women in AI Trailblazer Award. She has published 150+ papers in premier international journals and conferences. Her book “Responsible AI: Best Practices for Creating Trustworthy AI Systems” was published by Pearson Addison-Wesley in Dec 2023. This book is the world’s first responsible AI book for practitioners, which peaked at No.3 on Amazon’s AI book bestseller list.
Prof. Dr. Ingo Weber is Full Professor in the Computer Science Department, TUM School of Computation, Information and Technology, at Technical University of Munich, Germany. Ingo Weber is also Director of Digital Transformation and ICT Infrastructure at the Fraunhofer-Gesellschaft. Before moving to Munich, he was Full Professor of Software and Business Engineering at Technische Universität Berlin from 2019 to 2022. Before that, he spent ten years in Sydney, Australia, where he worked for the research institutions CSIRO, NICTA and UNSW. In 2009, he received his PhD from the University of Karlsruhe (TH), now KIT, and worked in parallel for SAP Research. In his research, Ingo Weber focuses on various subfields of computer science, in particular business process management and process mining, software architecture and engineering, DevOps, blockchain, and applied artificial intelligence (AI). He is author of numerous publications and co-author of the textbooks “DevOps: A Software Architect’s Perspective” (2015) and “Architecture for Blockchain Applications” (2019).
Dr. Liming Zhu is a Research Director at CSIRO’s Data61, the AI/digital arm of Australia’s national science agency, and a conjoint professor at UNSW. He contributes to the OECD.AI’s AI Risks and Accountability, the Responsible AI at Scale think tank at Australia’s National AI Centre, ISO AI standards committees, and Australia’s AI safety standard. His research division innovates in AI engineering, responsible/safe AI, blockchain, quantum software, privacy, and cybersecurity, and hosted Australia’s Consumer Data Right/Open Banking standards setting. Dr Zhu has authored over 300 papers and is a regular keynote speaker. He delivered the keynote “Software Engineering as the Linchpin of Responsible AI” at the International Conference on Software Engineering. His latest book, “Responsible AI: Best Practices for Creating Trustworthy AI Systems,” and his forthcoming book, “AI Engineering: Architecture and DevOps for AI Systems,” reflect his vision for the rigorous engineering of responsible and safe AI systems for society.