Aarush Gupta
Machine Learning Engineer at Snap Inc.
New York, New York, United States
Summary
👤
Senior🎓
Top SchoolAarush Gupta is a Machine Learning Engineer with nine years of experience, currently building and deploying ML systems at Snap in New York after earning an MSR at Carnegie Mellon and a CS degree from IIT Roorkee. He blends research-grade expertise (Harvard, ETS, CMU internships) with product-focused engineering, having shipped models for vision, language, and robotics across startups and labs. An active open-source contributor, he enhanced the C++ mlpack library by adding a FlexibleReLU activation with robust forward/backward passes and tests, improving stability and type handling. His background in mechatronics and automation informs practical solutions for perception and deployment, while leadership roles in student organizations and mentoring reflect strong collaboration and knowledge-sharing. Notably, he pairs deep model work (connectivity-aware segmentation, hybrid UNet approaches) with hands-on implementation across the full ML lifecycle.
9 years of coding experience
1 year of employment as a software developer
Indian Institute of Technology RoorkeeMaster of Science - MS, Mechatronics, Robotics, and Automation Engineering, Master of Science - MS, Mechatronics, Robotics, and Automation Engineering at Carnegie Mellon University
English, Hindi
Github Skills (13)
machine-learning10
deeplearning-ai10
deep-learning10
cpp10
cplus10
data-structure9
algorithm9
data-structures9
algorithms9
testing8
regression4
nearest-neighbor-search3
nearest-neighbors3
Programming languages (3)
Github contributions (5)
mlpack/mlpack
Feb 2018 - Mar 2018
mlpack: a fast, header-only C++ machine learning library
Role in this project:
ML Engineer
ML EngineerContributions:14 commits, 2 PRs, 11 comments in 6 days
Contributions summary:Aarush primarily contributed to the development of the mlpack library, focusing on the FlexibleReLU activation layer. Their work involved adding the FlexibleReLU layer, implementing its forward and backward passes, and creating associated tests. They also fixed build and typecasting errors, enhancing the library's functionality and stability.
regressionheaderdeep-learningscientific-computingc-plus-plus
aarushgupta/Video_Segmentation
Oct 2017 - Oct 2017
Contributions:2 commits, 1 push, 1 branch in 1 day
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.