Kulin Seth
Software Engineering Manager at VMware
Cupertino, California, United States
Summary
🤩
Rockstar🎓
Top SchoolKulin Seth is a Software Engineering Manager based in Cupertino with 11 years of experience building low-level systems for graphics, virtualization, and machine learning. He combines hands-on engineering (a decade as an individual contributor) with management responsibilities at Apple, while maintaining senior technical roles at VMware and Qualcomm focused on GPU/graphics and memory virtualization. His open-source contributions to TensorFlow and PyTorch reveal deep expertise in hardware integration and numerical primitives—adding MacOS pluggable device support and FP8 data types in TensorFlow and improving Metal Performance Shaders backend in PyTorch. He has a strong research foundation (MS in Computer Engineering, thesis on heterogeneous embedded architectures) and a track record of applying ML techniques to engineering problems like bug de-duplication. Comfortable shipping firmware-to-framework changes, Kulin is as likely to design a shader optimization or virtualization feature as to lead the team delivering it. His career shows a rare blend of GPU/driver internals, virtualization, and ML systems integration.
11 years of coding experience
13 years of employment as a software developer
Master of Science Computer Engineering Thesis Computer architecture embedded, Master of Science Computer Engineering Thesis Computer architecture embedded at Northeastern UniversityBachelor of Technology DSP Systems and Architecture Computer Organization and Architecture Digital System Design, Bachelor of Technology DSP Systems and Architecture Computer Organization and Architecture Digital System Design at National Institute of Technology Karnataka
Hindi
Stackoverflow
1reputation
0reached
0answers
0questions
Github Skills (13)
pytorch10
machine-learning10
deeplearning-ai10
p810
c-language10
deep-learning10
tensorflow10
cprogramming-language10
python10
gpu9
deep-neural-networks9
macos9
tensor9
Programming languages (7)
Github contributions (5)
pytorch/pytorch
Apr 2022 - Jan 2023
Tensors and Dynamic neural networks in Python with strong GPU acceleration
Role in this project:
Back-end Developer
Back-end DeveloperContributions:630 reviews, 96 commits, 133 PRs in 8 months
Contributions summary:Kulin primarily contributed to the PyTorch project by implementing and refining Metal Performance Shaders (MPS) for various operations. Their work focused on improving MPS heap volatility, adding support for adaptive max pool2d and other operators like eye and linspace. The user's contributions involved significant code changes related to the MPS backend, encompassing native implementations and test cases.
pythongpu-accelerationdeep-learninggpunumpy
tensorflow/tensorflow
Mar 2021 - Jan 2023
An Open Source Machine Learning Framework for Everyone
Role in this project:ML Engineer
ML EngineerContributions:40 reviews, 27 commits, 13 PRs in 1 year 10 months
Contributions summary:Kulin primarily focused on adapting the TensorFlow framework to support specific hardware and configurations. Their commits demonstrate modifications related to MacOS pluggable device support, including disabling certain checks and compilation paths. They also contributed to enabling new data types, particularly those related to FP8 formats, demonstrating expertise in numerical computation and hardware integration within the TensorFlow ecosystem.
pythondata-sciencedeep-learningmlmachine-learning
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.