I’m a researcher working on getting LLMs to reason via reinforcement learning at Google DeepMind. Most recently, I worked on AlphaProof, where we got an LLM to learn enough math to get a silver medal at the International Mathematical Olympiad, almost cracking the IMO grand challenge.

Previously, I worked on improving Google’s search ranking algorithm with deep learning.

You can reach me at rishicomplex@gmail.com.