Summary
Shiyu Song is a seasoned autonomy leader and staff engineer with ~8 years of experience building mapping, localization, and perception systems for self-driving vehicles, now focusing on dynamic scene understanding and mapping at Waymo. He helped found Baidu’s autonomous driving program and drove production-grade HD map pipelines and multi-sensor fusion localization that achieved fleet-scale, 5–10 cm accuracy and powered landmark demos and deployments. At TuSimple he led the calibration and mapping efforts behind the company’s first fully autonomous long-haul semi-truck run, and later guided SafeAI’s transition to learning-driven autonomy for heavy industrial vehicles deployed in mines and construction sites. His background spans both deep research (PhD-level training at UC San Diego) and hands-on production engineering, with strengths in scaling map services, sensor calibration, and integrating learned models into safety-critical stacks. Notably, he blends academic publication experience with fielded systems that operate across urban, highway, and subterranean environments.
8 years of coding experience
11 years of employment as a software developer
University of California, San Diego
Bachelor's degree Electrical Engineering, Bachelor's degree Electrical Engineering at Tsinghua University
Chinese, English