Di Wu
Director, Deep Learning Algorithm And Software at NVIDIA
San Francisco Bay Area United States
Summary
🤩
Rockstar🎓
Top SchoolDi Wu is a director-level deep learning and software leader with 11 years of experience building hardware-accelerated AI systems, currently driving AI deployment and efficiency at NVIDIA after the OmniML acquisition. He co-founded and led OmniML to productionize performant ML across data centers and edge devices, combining startup execution with enterprise-grade systems thinking. Previously he contributed to PyTorch hardware acceleration at Facebook and architected datacenter accelerator runtimes at Falcon Computing, grounding his leadership in low-level performance engineering. Di holds a Ph.D. in Computer Science from UCLA where his research focused on system design for domain-specific hardware acceleration across deep learning, medical imaging, and cognitive computing. He blends academic depth with product-driven engineering, able to translate research into scalable deployment pipelines that target diverse hardware. Based in the Bay Area, he’s known for marrying compiler/runtime insight with practical deployment tooling to make GPU AI both efficient and widely accessible.
10 years of coding experience
9 years of employment as a software developer
BS, Electrical Engineering, BS, Electrical Engineering at Tsinghua UniversityUniversity of California, Los Angeles
Github Skills (28)
python10
acceleration10
machine-learning10
numpy10
deep-learning10
tensorflow10
gpu10
autograd10
neural-network10
tensor10
gpu-acceleration10
hardware9
compiler6
bioinformatics5
genomics5
Programming languages (3)
Github contributions (5)
allwu/glow
Apr 2020 - Apr 2021
Compiler for Neural Network hardware accelerators
Contributions:23 pushes, 24 branches in 1 year
hardware-acceleratorscompilerneural-networkacceleratorshardware
falconcomputing/falcon-genome
Apr 2018 - Oct 2019
Contributions:2 PRs, 8 pushes, 2 branches in 1 year 6 months
pipelineacceleratedfalcongenomicsbioinformatics
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.