
I am a machine learning engineer at TikTok in San Jose, where I work on ads: the targeting and user-modeling systems that decide who sees which ad, from gender models covering more than two billion monthly users to LLMs fine-tuned on viewing history. At that scale a one percent gain is a large number, and most of my work is finding the next one.
Before TikTok I completed a master's in computer science at Stanford, focused on AI, while building research software: a GPT-4 pipeline that summarized 12,000 hours of group deliberation, a dyslexia screening platform used to assess more than 8,000 students, and VM allocation analysis at Microsoft Research. I started my career at Amazon, where I built an ML platform that retrained models across 19 marketplaces.
I also spent years in competitive programming, with two first-place finishes at the Gulf Programming Contest and first place in the UAE at Google Hash Code.
Outside of work I write AI Hoodman. Each post takes one real problem from ranking, recommendations or retrieval and explains the standard fix in a handful of slides.