[javaone2026] Running GPU-Accelerated AI Inference from Java at Uber Scale | Down Home Country Coding With Scott Selikoff and Jeanne Boyarsky (opens in new tab)

Speakers: Baojun Liu & Anshuman Mishra See the live blog table of contents Michelangelo Uber's unified ML platform 20K models trained/month 5.3 models in prod Java Online prediction is all Java High concurrency orchestration Business logic management Production ecosystem integration Spark ML pipeline C++ is ML runtime and Math libraries Java manages threads, coordinates execution, handles