# The Craft of Post-Training: A Practical Guide for AI Engineers and Developers

> Post-training is the process of adapting a pre-trained foundation model to specific tasks, domains, or behavioural requirements through techniques such as supervised fine-tuning (SFT), reinforcement learning from human feedback (RLHF), and direct preference optimisation (DPO). This book is a practical guide to turning foundation models into production-ready systems. By Chris von Csefalvay, published by No Starch Press (ISBN 9781718505209, 416 pages, available July 2026).

## Book Information
- [Homepage](https://posttraining.guide): Landing page with table of contents, learning objectives, and author information.
- [Buy from No Starch Press](https://nostarch.com/craft-of-post-training): Early Access and print pre-order.
- [Author Website](https://chrisvoncsefalvay.com): Author's personal site with research, papers, and blog.

## Topics Covered
- Supervised fine-tuning (SFT) with Low-Rank Adaptation (LoRA) and Quantised LoRA (QLoRA)
- Reinforcement learning from verifiable rewards (RLVR)
- Group Relative Policy Optimisation (GRPO)
- Direct Preference Optimisation (DPO), Kahneman-Tversky Optimisation (KTO), Odds Ratio Preference Optimisation (ORPO)
- Model evaluation, benchmark design, and regression detection
- Domain adaptation and specialisation (clinical, legal, enterprise)
- Agentic model training for sequential action-taking
- Quantisation, compression, and deployment optimisation
- Multimodal and vision-language alignment
- Synthetic data generation and RLAIF
- Reasoning capabilities and complex thought training

## Book Structure
- Part I: The Foundation (Chapters 1-2) — Post-training essentials and prerequisites
- Part II: The Tools (Chapters 3-6) — SFT, reinforcement learning, preference optimisation, evaluation
- Part III: The Craft (Chapters 7-10) — Quantisation, domain adaptation, agentic models, reasoning
- Part IV: The Frontier (Chapters 11-13) — Synthetic data, multimodal systems, future directions

## Author
- [Chris von Csefalvay](https://chrisvoncsefalvay.com): Principal at HCLTech's AI Practice, leading post-training research and clinical intelligence. Author of Computational Modeling of Infectious Disease (Elsevier, 2023). Degrees from Oxford and Cardiff. Fellow of the Royal Society for Public Health, IEEE Senior Member.
- [Google Scholar](https://scholar.google.com/citations?user=X_2G-VsAAAAJ): Publication record and citations.
- [ORCID](https://orcid.org/0000-0003-3131-0864): Persistent author identifier.
- [LinkedIn](https://www.linkedin.com/in/chrisvoncsefalvay/): Professional profile.

## Optional
- [Wikidata Entity](https://www.wikidata.org/wiki/Q107095298): Structured data about the author.
- [GitHub](https://github.com/chrisvoncsefalvay): Code repositories and companion notebooks.