ML Research Engineer | LLM Optimization & Efficiency | Authoring “Rearchitecting LLMs” @Manning | 1.9K GitHub ⭐
I work at the intersection of applied research and production engineering: how to make large models faster, smaller, and fairer without sacrificing what makes them useful.
I'm currently writing Rearchitecting LLMs with Manning.
I wrote this book because I couldn't find any resource that explained, rigorously and practically, what happens when you need to take a large model and adapt it for real production: reduce its size, specialize it, make it more efficient, and understand which capabilities you lose — and which ones, surprisingly, improve.
It covers structural pruning, knowledge distillation, attention bypass, dynamic inference, and fairness pruning. Not from theory, but from reproducible experiments on real models.
Available in Early Access (MEAP): https://hubs.la/Q040tvtp0
I write about model optimization, AI ethics, and the future of agents.
