RahulRahul is the name Buddha gave to his son ChandChand means "moon" in Sanskrit

Hi, I am Rahul. I am currently a MSCS student at Stanford 🌲 . Previously I was an intern at the GEAR Lab at NVIDIA Research working on GR00T N1.6 and offline RL. . Before that, I was an intern at NVIDIA's post-training Nemotron LLM team working on latent reasoning, and contributed to Nemo-RL (async RL) and Nemo-Gym.

I was also part of the ILIAD group (Dorsa Saidgh's lab). Prior to joining Stanford 🌲 I worked as a Research Fellow at Microsoft Research on Transformer Compression & Extreme Classification. My current interests are in RL+LLM and Robotics (You can have super intelligence in an API for 20$/month but it would still be fundamentally limited unless you can give it a physical body).

At Stanford I have also been a TA for:

• CS 153 — Infra at Scale (Anjey Midha A16z, Michael Abbot)
• CS 234 — Reinforcement Learning (Emma Brunskill)
• CS 224R — Deep RL (Chelsea Finn)

In the future I look forward to getting replaced by AGI and work as a Wallace design protein farmer.

In my previous life, I completed my undergrad in CS from BITS Pilani. For more details, check my CV.