Summary
Emma W is a Senior Staff Software Engineer at Google DeepMind with 11 years of experience specialising in serving system design and performance optimization for large multimodal models. She leads the Multimodal Serving team that delivered multi-fold speedups across Genie, Veo, Nano Banana and Gemini-based products, routinely combining compiler, model, and runtime optimizations to improve both latency and throughput. A Harvard PhD in computer architecture, she has a track record of productionizing autotuning and automatic model-partitioning systems that saved fleet TPU resources and set MLPerf records. Emma balances deep research pedigree with hands-on systems engineering and has repeatedly turned academic techniques into deployable, fleet-scale impact. Her open-source work and public homepage reflect a continued focus on speeding up machine learning across hardware and software stacks.
11 years of coding experience
6 years of employment as a software developer
Doctor of Philosophy (PhD), Computer Science, Doctor of Philosophy (PhD), Computer Science at Harvard University
Bachelor's degree, Computer Science, Bachelor's degree, Computer Science at Shanghai Jiao Tong University