Amrith Setlur
Graduate Research Assistant
Pittsburgh, Pennsylvania, United States
Summary
👤
Senior🎓
Top SchoolAmrith Setlur is a PhD student and graduate research assistant in machine learning with a decade of industry and academic experience spanning BAIR/CMU and major tech labs. He has built and deployed production ML systems at Amazon that moderated 32% of ad traffic and improved claim-detection recall by 25%, and has research internships at Apple and Google. His work blends large-scale applied engineering—distributed metadata services and low-latency retrieval—with advanced deep learning and semi-supervised techniques for multi-modal and cross-lingual problems. A President’s Gold Medalist from NIT Trichy and a CMU alumnus, he pairs rigorous theoretical research (approximation algorithms early in his career) with pragmatic product impact. Based in Pittsburgh, he moves fluidly between research and production, turning unlabeled data and noisy real-time streams into robust, deployable models. Notably, his background includes both creating structured validation languages for real-time pipelines and advancing state-of-the-art attention networks for ad understanding.
10 years of coding experience
2 years of employment as a software developer
President Gold Medalist, Computer Science (Hons.), President Gold Medalist, Computer Science (Hons.) at National Institute of Technology, TiruchirappalliDoctor of Philosophy - PhD, Machine Learning, Doctor of Philosophy - PhD, Machine Learning at Carnegie Mellon UniversityCBSE Class XII, Mathematics and Computer Science, XII, CBSE Class XII, Mathematics and Computer Science, XII at Apeejay School
English, Hindi, Tamil, German, Kannada
Github Skills (18)
few-shot-learning7
meta-learning6
meta6
convex5
image-classification4
convex-optimization4
ocr4
optimization4
detector3
nlp3
scene3
react3
pytorch3
javascript2
gradient-descent2
Programming languages (2)
Github contributions (5)
ars22/WorkflowScheduling
Mar 2017 - Mar 2017
Contributions:5 commits, 5 pushes, 1 branch in 9 days
OscarcarLi/meta-analysis-classification
Apr 2020 - Jul 2021
Contributions:175 pushes, 10 branches in 1 year 2 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.