Summary
Weizhuo Zhang is a Senior Test Development Engineer with eight years of experience building and validating AI and compute software across Intel, NVIDIA, Huawei, and SenseTime. He specializes in CI/CD and automated validation for PyTorch and CPU backends (IPEX, Inductor), cross-platform build and compatibility testing, and large-model automated test suites for architectures like ResNet, BERT, GPT-J, LLaMA and Stable Diffusion. Comfortable across Linux, Docker, diverse GCC toolchains and embedded platforms, he has deep hands-on experience migrating and optimizing software for ARM and heterogeneous hardware. A vim enthusiast with a strong interest in ML theory, deep learning and reinforcement learning, he combines low-level systems know-how with practical ML model validation to bridge research and production. Based in Shanghai, he often surfaces root causes by tracing performance regressions to specific commits and driving fixes upstream.
8 years of coding experience
6 years of employment as a software developer
Study Abroad, Software Engineering, Study Abroad, Software Engineering at The University of Queensland
学士, 软件工程, 学士, 软件工程 at 中南大学
The University of Melbourne