Patric Zhao
Chief GPU Software Architect at East China Normal University
California, United States
Summary
👤
Senior🎓
Top SchoolPatric Zhao is a Chief GPU Software Architect based in California with 12 years of experience building high-performance computing and deep learning systems across Intel, NVIDIA, and Cadence. He specializes in bridging high-level algorithmic optimization with low-level hardware tuning—vectorization, multi-threaded/multi-process parallelization, and hot-spot performance engineering—to accelerate frameworks such as TensorFlow, PyTorch, Caffe and MXNet. His career spans roles from hands-on senior engineering to technical leadership across global teams in Shanghai and Silicon Valley, and he also contributes to academia as a visiting assistant professor. Known for squeezing maximum throughput from GPU and compiler stacks, he combines research rigor from a Master’s in Parallel Computing with practical production delivery of optimized AI pipelines.
12 years of coding experience
18 years of employment as a software developer
Master Parallel Computing, Master Parallel Computing at Ningxia Universitycourseraningxia
Stackoverflow
2,093reputation
675kreached
29answers
2questions
tensorflow
top-5%
machine-learning
top-5%
linux
top-5%
gpu
top-5%
environment-variables
top-5%
gpgpu
top-5%
Github Skills (26)
gpgpu9
environment-variables9
linux9
machine-learning9
tensorflow9
gpu9
mutation8
julia8
mxnet8
dep8
portable8
dataflow7
javascript7
parallel7
golang7
Programming languages (1)
Github contributions (5)
PatricZhao/ParallelR
Apr 2016 - May 2019
Contributions:62 commits, 3 PRs, 61 pushes in 3 years
acceleratetechnologiesparallel
PatricZhao/ParallelGrep
Apr 2014 - May 2019
Contributions:16 commits, 18 pushes, 9 comments in 5 years 1 month
Find and Hire Top DevelopersWe’ve analyzed the programming source code of over 60 million software developers on GitHub and scored them by 50,000 skills. Sign-up on Prog,AI to search for software developers.