Harshan Baskar
Software Engineer 2 at Microsoft
Tamil Nadu, India
Summary
🤩
Rockstar🎓
Top SchoolHarshan Baskar is a Software Engineer 2 at Microsoft with eight years' experience building cloud-native backends, networking features, and AI-powered systems. A BITS Pilani computer science graduate, he has worked across Azure Load Testing, robotics-focused computer vision, and networking internships at Cisco, blending production engineering with research-driven ML. He contributes to prominent open-source ML projects such as CuPy and Chainer, where he improved CUDA bindings and ChainerX kernels—work that ties low-level GPU compute to higher-level deep learning frameworks. Comfortable with Docker, Kubernetes, Linux, IPv4/DNS/routing, and Azure services, he repeatedly bridges infrastructure and ML needs to ship reliable systems. Based in Tamil Nadu, Harshan uniquely pairs hands-on CUDA/Cython fixes with cloud-scale service engineering, making him effective at optimizing both model execution and platform reliability.
8 years of coding experience
3 years of employment as a software developer
BITS Pilani, Birla Institute of Technology and Science
Stackoverflow
67reputation
17kreached
4answers
9questions
Github Skills (22)
cublas10
python10
chainer10
machine-learning10
numpy10
deeplearning-ai10
deep-learning10
gpu10
cuda10
cython9
cprogramming-language8
c178
c118
c-language8
html6
Programming languages (11)
Github contributions (5)
cupy/cupy
Feb 2020 - Apr 2020
NumPy & SciPy for GPU
Role in this project:
Back-end Developer
Back-end DeveloperContributions:39 commits, 9 PRs, 38 comments in 1 month
Contributions summary:Harshan primarily focused on modifying and extending the `cupy/cuda` and `cupy/cuda/cusparse` modules, which provide CUDA bindings for linear algebra routines. Their contributions include improvements related to cuBLAS and cuSPARSE handles and implementations. The user also fixed import statements in Python and Cython files and added the necessary `intptr_t` import statements to multiple modules.
cudapythoncusolvergpunumpy
chainer/chainer
Mar 2019 - Apr 2019
A flexible framework of neural networks for deep learning
Role in this project:ML Engineer
ML EngineerContributions:34 commits, 7 PRs, 25 comments in 27 days
Contributions summary:Harshan primarily contributed to the ChainerX implementation within the Chainer deep learning framework. Their work included implementing the ChainerX version of the Clipped ReLU forward function, fixing import issues, and updating existing files. Further contributions involved modifying the ChainerX ArgMin implementation, which included modifications to native and CUDA device implementations.
cudapythonmxnetcaffe2flexible-framework
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.