Abhinav Gupta is a Research Scientist at Google DeepMind with 11 years of experience focused on the intersection of reinforcement learning and language, particularly fine-tuning large language models with machine/execution feedback and robust evaluation metrics. He brings a strong research pedigree from a PhD at Université de Montréal and hands-on internships across Google, Microsoft, Meta, Adobe and CMU, where he applied RL, self-play and offline methods to problems from emergent communication to code correctness. At DeepMind he contributes to the Gemini post-training team, building production-facing model improvements informed by execution feedback and multi-turn self-repair. His work uniquely combines multi-agent and emergent communication insights with practical alignment techniques for LLMs, reflecting both theoretical depth and applied impact. Based in London, he has a track record of turning novel RL ideas into measurable gains in complex environments and production research projects.
11 years of coding experience
1 year of employment as a software developer
BITS Pilani, Birla Institute of Technology and Science
Doctor of Philosophy - PhD Computer Science, Doctor of Philosophy - PhD Computer Science at Université de Montréal
Master’s Degree Computer Science, Master’s Degree Computer Science at New York University
Contributions:5 commits, 5 pushes, 1 branch in 1 year 3 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.
Request Free Trial
Abhinav Gupta - Research Scientist at Google DeepMind