Vrajang Parikh
Founder at Tenjin
Redmond, Washington, United States
Summary
🤩
Rockstar🎓
Top SchoolVrajang Parikh is an AI software engineer with seven years of hands-on experience building high-performance systems and machine learning tooling, currently working on ONNX Runtime Mobile at Microsoft in Redmond. He has a strong backend focus demonstrated by contributions to the flagship microsoft/onnxruntime project—adding training API bindings for Objective-C/Swift, checkpointing, activation ops, and CoreML-oriented implementations. His background spans ML compiler work, game and engine programming, and production feature delivery at scale (including features for a game with over a million daily users), reflecting versatility across performance-critical domains. Vrajang blends research and product experience from University of Waterloo roles and multiple Microsoft internships to bridge low-level systems engineering with developer-facing ML APIs. Notably, he brings cross-platform interoperability chops—enabling training and debugging workflows on mobile and Apple platforms that aren’t obvious from a title alone. He is driven by optimizing runtime performance while making advanced ML capabilities accessible to application developers.
7 years of coding experience
4 years of employment as a software developer
BCS + Artificial Intelligence Specialization Computer Science, BCS + Artificial Intelligence Specialization Computer Science at University of Waterloo
Github Skills (11)
objective-c10
c-language10
onnx10
cprogramming-language10
coreml10
machine-learning9
deep-learning8
tensorflow7
pytorch7
ai-framework7
hardware-acceleration6
Programming languages (7)
Github contributions (5)
microsoft/onnxruntime
May 2023 - May 2026
ONNX Runtime: cross-platform, high performance ML inferencing and training accelerator
Role in this project:
Back-end Developer
Back-end DeveloperContributions:2 releases, 94 reviews, 54 PRs in 3 years
Contributions summary:Vrajang primarily contributes to the backend of the ONNX Runtime project. Their work includes adding attributes for debugging purposes and implementing Objective-C bindings for the training APIs, including checkpoint functionality and the ORTTrainingSession. The user also added support for various activation operations such as Sigmoid, Relu, and Tanh, and implemented Transpose and Split operations using ML programs, enhancing support for CoreML. These changes indicate a focus on extending the functionality and platform compatibility of the project, particularly for training and CoreML integration.
machine-learningonnxruntimedeep-learningonnxneural-networks
vraspar/onnxruntime
May 2023 - Apr 2026
ONNX Runtime: cross-platform, high performance ML inferencing and training accelerator
Contributions:4 PRs, 83 pushes, 6 branches in 2 years 11 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.