Siju Samuel
Deep Learning R&D Engineer at Intel Corporation
Bengaluru, Karnataka, India
Summary
🤩
Rockstar🎓
Top SchoolSiju Samuel is a Deep Learning R&D Engineer and AI system architect with nearly two decades of experience designing compilers, model-optimization pipelines, and distributed training systems for specialized accelerators (HPU/NPU). Currently at Intel (Habana), he bridges PyTorch to HPU and optimizes large-scale training for models from ViT and YOLO to BERT and LLaMA, while driving quantization and performance work upstream in TensorFlow and PyTorch. An active open-source committer—once the second-highest contributor to Apache TVM in 2020—he has made practical compiler fixes in projects like XLA and TVM that improve build robustness and operator support. His background at Huawei includes leading lightweight model research and production-serving extensions, reflecting a rare combination of low-level compiler expertise and hands-on model deployment. Based in Bengaluru, he blends systems-level thinking with a pragmatic focus on scalability and efficiency, often making small, high-leverage contributions that prevent subtle runtime issues.
8 years of coding experience
8 years of employment as a software developer
Post Graduate Program in Artificial Intelligence & Machine Learning, Artificial Intelligence, Excellent, Post Graduate Program in Artificial Intelligence & Machine Learning, Artificial Intelligence, Excellent at The University of Texas at AustinBachelor of Technology - BTech, Electrical, Electronics and Communications Engineering, CGPA 8.4, Bachelor of Technology - BTech, Electrical, Electronics and Communications Engineering, CGPA 8.4 at Cochin University of Science and Technology
English, Chinese, Malayalam, Kannada
Stackoverflow
1reputation
0reached
1answer
0questions
Github Skills (14)
debugging10
compiler10
debug10
c-language10
cprogramming-language10
protobuffer9
protobuf9
tensorflow9
onnx9
compiler-optimization9
machine-learning8
android-ndk6
android6
documentation6
Programming languages (8)
Github contributions (5)
apache/tvm
Jan 2018 - Nov 2020
Open deep learning compiler stack for cpu, gpu and specialized accelerators
Role in this project:
Backend Developer & ML Engineer
Backend Developer & ML EngineerContributions:43 reviews, 141 commits, 162 PRs in 2 years 9 months
Contributions summary:Siju's contributions primarily focused on addressing compilation warnings and resolving type-related issues within the codebase. They fixed issues such as uninitialized variables, signed/unsigned integer comparisons, and enum usage in boolean contexts. Furthermore, the user updated documentation and addressed Pylint issues. Notably, the user also added support for operations in the core of a deep learning compiler, including ReLU and the addition of operators within the Tensorflow and Onnx frontends.
metalvulkancompilertensoropencl
openxla/xla
Dec 2018 - Feb 2019
A machine learning compiler for GPUs, CPUs, and ML accelerators
Role in this project:Back-end Developer
Back-end DeveloperContributions:13 commits in 2 months
Contributions summary:Siju primarily contributed to the XLA compiler by fixing minor code inconsistencies and making small adjustments to existing files. Their commits involved updating header files and proto definitions to address grammatical errors like typos. The user also made improvements in multiple files related to XLA's internal mechanisms and configuration.
compilercommunity-drivenmachine-learningmodular
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.