Summary
Chenghao Li is a research-driven engineer and Fundamental Research Lead specializing in 3D vision, generative AI, and robotics, with eight years of experience spanning internships to leadership roles in industry and academia. He holds a PhD from Shanghai Jiao Tong University and combines deep expertise in local feature learning, scene representation, and animatable NeRF-based avatars with hands-on systems work—designing VAEs, scalable data pipelines, and reward models for SFT/RLHF. At MiniMax and Pika he contributed to large-scale text-to-image/video foundations and real-time video chat architectures, and has production experience optimizing models for mobile and edge deployment. Unusually, his background blends mechatronics-powered robotics projects (VSLAM, ROS platforms, underwater ROV control) with state-of-the-art generative model engineering and dataset curation at 10B+ scale. Based in Palo Alto, he is actively seeking postdoc or research scientist roles where he can bridge foundational research and deployable multimodal systems.
8 years of coding experience
1 year of employment as a software developer
Master of Engineering - MEng, Mechanical Engineering, Master of Engineering - MEng, Mechanical Engineering at East China University of Science and Technology
Doctor of Philosophy - PhD, Computer VIsion, Robotics, Doctor of Philosophy - PhD, Computer VIsion, Robotics at Shanghai Jiao Tong University