Adithya Devraj
Applied Scientist II at Amazon
San Francisco Bay Area United States
Summary
👤
Senior🎓
Top SchoolAdithya Devraj is an applied scientist with eight years of experience translating advanced reinforcement learning theory into practical solutions, currently working on LLM alignment at Amazon. He holds a PhD from the University of Florida focused on fast RL algorithms and asymptotic variance optimization, followed by a Stanford postdoc on exploration strategies, and has applied that research in industry roles at Ford and multiple ML research internships. His work bridges stochastic control, optimization, and machine learning, with a track record of developing theoretically grounded algorithms that scale to real problems. Based in the San Francisco Bay Area, he combines deep academic rigor with hands-on engineering in production settings—an approach evident from his transitions between top research labs and applied industry teams. An atypical strength is his consistent focus on variance-aware algorithm design, which informs both robust empirical performance and principled alignment work on large models.
8 years of coding experience
8 years of employment as a software developer
Doctor of Philosophy (Ph.D.), Electrical and Computer Engineering, 3.88, Doctor of Philosophy (Ph.D.), Electrical and Computer Engineering, 3.88 at University of FloridaHigh School, PCMB (Physics, Chemistry, Maths and Biology), High School, PCMB (Physics, Chemistry, Maths and Biology) at Christ College - BangaloreBachelor's Degree, Telecommunications Engineering, 8.17, Bachelor's Degree, Telecommunications Engineering, 8.17 at PES Institute of TechnologyPostdoctoral Fellowship, Electrical and Computer Engineering, Postdoctoral Fellowship, Electrical and Computer Engineering at Stanford University
English, Kannada, HindiGithub contributions (3)
adidevraj/SVRPDA
Oct 2019 - Dec 2019
Contributions:7 commits, 6 pushes, 1 branch in 1 month
adidevraj/Zap-Q-learning-for-stochastic-shortest-path-problem
Dec 2017 - Jan 2018
Contributions:8 commits, 7 pushes, 1 branch in 1 month
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.