Keith Mok is an embedded software engineer with 26 years of experience building and shipping Linux/Android systems, from board bring-up to production-grade deep learning edge integrations. He has led BSP, kernel driver and device security efforts across NXP, TI, Qualcomm, NVIDIA and Xilinx platforms, and has a track record of turning prototypes into manufacturable products. At companies including Google, Density and Barnes & Noble he focused on performance tuning, Android HAL architecture and trusted-boot/security for factory workflows. An active open-source contributor, his patches span the mainline Linux kernel, Android/LineageOS, Buildroot and Arm NN (adding dilation/deconvolution support and fixing TfLite/Yolo issues), highlighting a rare blend of low-level systems expertise and ML-edge pragmatism. Based in Bellevue, WA, he combines architect-level design reviews with hands-on kernel/driver implementation and manufacturing/tooling experience.
Arm NN ML Software. The code here is a read-only mirror of https://review.mlplatform.org/admin/repos/ml/armnn
Role in this project:
ML Engineer
Contributions:10 commits, 8 PRs, 51 comments in 2 months
Contributions summary:Keith Mok's contributions primarily involved enhancing the Caffe parser within the Arm NN ML software repository. He added support for dilation and deconvolution layers, crucial for handling certain network architectures. Furthermore, he fixed build breaks and a crash in the related TfLite benchmark, improving its stability and usability. In addition, he fixed a bug within the YoloV3Big test program.
Contributions:16 commits, 8 pushes in 3 years 6 months
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.