Building a specialized model requires a variety of decisions. This free ebook helps you make sense of them, from choosing training examples and fine-tuning your model to planning experiments that make good use of your testing budget. Across five complementary chapters from Manning books, you’ll explore Bayesian optimization through a compiler example, examine the strengths and limitations of LLM judges, and investigate runtime performance with ONNX profiling. You’ll come away with practical methods you can apply as you develop, evaluate, and refine your own models.
about the authors
Amit Bahree is CTO in the office of the CEO at G42 Americas, where he leads engineering and AI platform strategy. Previously, he led Applied AI Engineering in Core AI at Microsoft, covering Azure OpenAI, Azure AI Services, and agentic systems across training, inference, and customization at cloud scale. He holds multiple patents, pursued applied software-engineering research at the University of Oxford, and is the author of several books on AI and software, including
Generative AI in Action and
Practical Weak Supervision.
Weehyong Tok is Partner, Director of Product Management at Microsoft, with over 18 years of experience driving product strategy for Microsoft’s data and AI platforms. He previously served as Head of AI Labs, leading global AI strategy and innovation. He holds a PhD in Computer Science from the National University of Singapore, specializing in large-scale database and data streaming systems and AI in query processing, and he is the author of more than 10 books on AI and data, including
Practical Weak Supervision and
Practical Automated Machine Learning.
Walid Amamou is the founder and CEO of UbiAI.tools, a leading fine-tuning platform used by Fortune 500 companies and enterprise AI teams. He holds a Ph.D in Physics and is a patent holder for ”Systems and methods for automated text labeling”. He has years of hands-on experience deploying LLMs in production and advising data scientists, AI engineers, and product managers on model optimization. His work focuses on fine-tuning for compliance-critical and industry-specific applications.
Alessandro Negro is Chief Scientist at GraphAware, where he designs domain-specific knowledge graph and LLM solutions for regulated industries. He is the author of two previous Manning books,
Graph-Powered Machine Learning and Knowledge Graphs and
LLMs in Action. His expertise spans knowledge graphs, graph neural networks, NLP, and specialized language models.
David Sweet has worked as a quantitative trader at GETCO and a machine learning engineer at Instagram. He teaches in the AI and Data Science master's programs at Yeshiva University.
Han Lee has spent more than a decade applying cutting-edge research on large-scale AI and machine learning systems into production‐grade products. A Senior Director of Data and AI at Moody’s, he leads teams that ship generative AI applications and has daily, hands-on exposure to safety-critical evaluation pipelines.
Guglielmo Iozzia is a Director of AI and Applied Mathematics at Merck & Co. and a Distinguished Member of the American Society for Artificial Intelligence. He specializes in AI biomedical applications.