Ameesh Shah

research contact home

Hi! I'm currently a Second Year Ph.D student at UC Berkeley, where I'm advised by Sanjit Seshia, and gratefully supported by the NDSEG Fellowship.

My research interests lie primarily at the intersection of machine learning and formal methods. In particular, I'm hoping to make AI more trustworthy by creating algorithms that can learn and reason in symbolic and interpretable ways. In doing so, we can create AI systems that are easier to understand, verify, and compose, which can help us adopt them in real-world scenarios. I'm currently working on "symbolic AI" in the context of Robotics and Inverse Reinforcement Learning, Safe Autonomy, and Program Synthesis. Please see my research for some examples of this intersectional work if you're interested.

I received my Bachelor's and Master's degrees from Rice University, where I worked at the intersection of program synthesis and machine learning. I was advised by Swarat Chaudhuri, who I worked with on the "Understanding the World Through Code" NSF Expeditions Project. As an undergrad, I also worked on projects with Ankit Patel and Richard Baraniuk. I was fortunate to be supported by the Rice CS Graduate Fellowship.

I've also spent time at Microsoft Research AI, where I worked with Alex Polozov and the GRAIL group on interactive ML-driven program synthesis.

In my free time, I enjoy doing a lot of things, including but not limited to: playing tennis, buying sneakers, cooking, fixing and breaking my jumpshot, and generally vibing. I'm originally from Cleveland, Ohio, and I love watching my beloved Cavaliers and Browns break my heart year after year.