Mohamad Katanbaf
Senior Embedded Software Engineer at Amazon
Greater Seattle Area United States
Summary
🤩
Rockstar🎓
Top SchoolMohamad Katanbaf is a Senior Embedded Software Engineer with eight years of experience building low-level runtime and connectivity features for edge and embedded systems. He has held embedded roles at Amazon and OctoML and brings a strong research foundation from a PhD program at the University of Washington. Mohamad contributes to high-profile open-source work such as the TVM compiler, where he improved RPC runtime, cross-platform build portability, and emulator support—highlighting his expertise at the intersection of ML tooling and embedded platforms. He is experienced with Zephyr and low-level communication stacks, suggesting a knack for making complex hardware-software integrations robust and portable. Based in the Greater Seattle Area, he pairs academic rigor with production engineering to ship reliable embedded runtime features. Colleagues would note his uncommon combination of deep systems troubleshooting and practical cross-platform build fixes that accelerate deployment on diverse targets.
8 years of coding experience
11 years of employment as a software developer
Doctor of Philosophy - PhD Electrical and Computer Engineering, Doctor of Philosophy - PhD Electrical and Computer Engineering at University of WashingtonMaster of Science (M.Sc.) Electrical and Electronics Engineering, Master of Science (M.Sc.) Electrical and Electronics Engineering at Sharif University of Technology
Github Skills (13)
c1710
embedded10
rpc10
c1110
sys10
zephyr9
compiler-compiler8
compiler8
vulkan4
gpu4
deep-learning3
deeplearning-ai3
machine-learning3
Programming languages (1)
Github contributions (5)
apache/tvm
May 2022 - Jan 2023
Open deep learning compiler stack for cpu, gpu and specialized accelerators
Role in this project:
Back-end Developer / Embedded Systems Engineer
Back-end Developer / Embedded Systems EngineerContributions:114 reviews, 12 commits, 17 PRs in 8 months
Contributions summary:Mohamad primarily contributed to the runtime aspects of the TVM compiler, specifically focusing on RPC (Remote Procedure Call) functionality. Their work included implementing RPC logging, addressing build issues, and unifying the `ssize_t` definition for Windows builds. They also worked on the `minrpc` server, which suggests they contributed to the low-level communication layers of the project. Additionally, they added support for the FVP emulator in the Zephyr platform, demonstrating experience with embedded systems and related tooling.
metalvulkancompilertensoropencl
mkatanbaf/tvm
Mar 2022 - Mar 2023
Open deep learning compiler stack for cpu, gpu and specialized accelerators
Contributions:300 pushes, 28 branches in 1 year
cpugpu-programmingcudagpu-accelerationtvm
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.