Hi, I'm Farit Galeev

I'm a machine learning engineer.

I build recommendation, ranking, and search systems that serve millions of users, and I treat each one as working only when it wins an A/B test. Currently, I'm a Data Scientist at Rakuten in Tokyo, serving foundation models in production on NVIDIA Triton. Along the way, I also...

• Built the personalized home feed and the push, cold-start, and "also buy" recommenders at Uzum Market (~20M monthly users). Each one won its A/B test, with gains of up to +18.7% ARPU and +83% push-to-order (cumulative through series of A/B tests)
• Built search autocomplete and query understanding for a national marketplace at Magnit Market (former KazanExpress).
• Write here about LLMs, recommendation systems, and other interesting topics.
• Mentor interns and ML Engineers