Arnav Deshpande
Hi - I’m Arnav! I’m a machine learning engineer at Palo Alto Networks and a recent UC Berkeley graduate. I’m especially interested in AI safety and created this website to share some related projects I’ve worked on. Outside of work, I am currently a SPAR AI Safety Research Fellow and a former AI researcher at Algoverse. My current projects mainly focus on model preferences, multi-agent evaluations, and reward hacking, but I’m also open to exploring other areas of safety research. In my free time, I love staying active, playing the guitar, mma, and traveling! Feel free to reach out if any of my work interests you!!
