Varul Srivastava
AI Researcher – Pre-Doctoral Researcher @ Google DeepMind
About
I am an AI Researcher at Google DeepMind, focused on improving reasoning capabilities of foundation models, particularly in the domain of healthcare. My research interests span Reinforcement Learning, Multi-Agent Systems, and post-training techniques for generative models.
I completed my B. Tech. + M. S. by Research in Computer Science at IIIT Hyderabad, where I worked at the Machine Learning Lab under Prof. Sujit Gujar on game theory and mechanism design with applications to multi-agent systems.
Previously, I was a Research Intern at Microsoft Research India, working with Rahul Sharma on LLM-based superoptimizers for straight-line C programs. I have also worked as an Applications Developer at Oracle in the Supply Chain Management (Fusion) team, and as an ML Engineer at Game Theory India.
Announcements
No announcements yet.
Experience
Part of the AQUA (Agents) team at the Foundational Research Unit. Working on improving System-2 type reasoning capabilities of Foundation Models with Vaibhav Rajan.
Designed and implemented agentic workflows for Value-Chain Planning products. Focused on developing enterprise solutions for supply chain optimization.
Worked with Rahul Sharma on LLM-based superoptimizers for compilers, optimizing arbitrary-sized code windows in straight-line C programs.
Designed and implemented an Elo-based learnable rating and matching system for player-to-player matching and performance evaluation platform.
Education
- Gold Medalist – CGPA 9.65
- Dean's List – 2019–2023
- Research Award – 2023
- Class Valedictorian – 98.75%
- Best All Rounder – Senior Class
Publications
Loading publications...
Get in Touch
I'm always interested in discussing research, AI, and building interesting systems. Feel free to reach out!