Summary
Qianhao Z is a Senior Software Engineer specializing in perception, with nine years of experience building and optimizing deep learning infrastructure and multi-sensor perception models at Nuro and prior research roles at CMU, UC Berkeley, and SenseTime. He combines hands-on model compression, quantization, and deployment expertise—having delivered 5x speedups for mobile demosaicking and 50% channel-pruned CNNs for quad-bayer pipelines—with backend-agnostic infra that accelerates SOTA training and deployment. Comfortable across Python, C++, and embedded toolchains, he has bridged research and production by shipping conversion/profiling tooling used broadly across teams and by implementing novel layers to halve model iteration cycles. Notably, he has experience synthesizing large-scale datasets and improving visual-inertial SLAM stability, reflecting a rare mix of low-level camera processing and high-level perception modeling.
9 years of coding experience
4 years of employment as a software developer
Bachelor of Engineering - BE Computer Science and Technology, Bachelor of Engineering - BE Computer Science and Technology at Beihang University
Exchange Program Computer Science, Exchange Program Computer Science at University of Toronto
Master of Science - MS Computer Vision, Master of Science - MS Computer Vision at Carnegie Mellon University
English, Chinese