Mudit Verma
Research Scientist at Google DeepMind
Mountain View, California, United States
Summary
👤
Senior🎓
Top SchoolMudit Verma is a research scientist with a decade of experience focused on reinforcement learning, preference-based RL/RLHF, and building LLM agents and vision–language models with an eye toward explainability and human-aware AI. Currently at Google DeepMind working on Gemini after a PhD at Arizona State University, he blends rigorous academic research with hands-on industry impact at Apple and Google where his work on preference-based RL reached ICLR attention. He has a strong applied background in RL for robotics and navigation, systems optimization (including quantized model analysis), and practical tooling from internships at Intel and Samsung. Based in Mountain View, he pairs deep algorithmic expertise with a knack for translating human preferences into scalable agent behavior—an often overlooked strength that informs his XAI and human-centric AI work.
10 years of coding experience
7 years of employment as a software developer
Bachelor of Technology (B.Tech.) Information Technology, Bachelor of Technology (B.Tech.) Information Technology at Delhi Technological University (Formerly DCE)Doctor of Philosophy - PhD Computer Science, Doctor of Philosophy - PhD Computer Science at Ira A. Fulton Schools of Engineering at Arizona State UniversityHigher Secondary Education Sciences, Higher Secondary Education Sciences at Ramjas School Pusa Road
English, Hindi
Github Skills (89)
api9
nlp9
python9
deep-learning9
pytorch9
machine-learning9
stock-prediction9
speech-recognition9
reinforcement-learning-environments9
natural-language-processing9
q-learning8
transformer8
language-model8
generative8
gymnasium8
Programming languages (8)
Github contributions (5)
famishedrover/famishedrover.github.io
Sep 2017 - Oct 2024
Contributions:1 PR, 45 pushes, 3 branches in 7 years 2 months
famishedrover/opencvexperiments
Aug 2017 - Aug 2017
Contributions:15 pushes, 1 branch in 12 days
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.