Manya Bansal

Profile photo

I’m a member of technical staff at humans&.

I’m currently on leave from my Ph.D. program at MIT, where I worked with Saman Amarasinghe and Jonathan Ragan-Kelley on programming languages for high performance computing.

My research is about helping programmers write fast, low-level GPU code that is still modular, reusable, and correct. I believe programming systems should give people precise control over hardware while making that control easier to compose and trust.

Before MIT, I was an undergraduate at Stanford, where I studied mathematics and received my B.S. in 2023. At Stanford, I was lucky to work with Fredrik Kjolstad and Dawson Engler, who let me tinker and build many, many small things.

News

  • May 2026 Our paper “Modular GPU Programming with Typed Perspectives” received a Distinguished Paper Award at PLDI'26.
  • Feb 2026 Gave a talk at Cornell’s Programming Languages Discussion Group on How to (not) Program GPUs.
  • Jan 2026 Joined humans& and went on leave from my Ph.D. program at MIT.
  • Dec 2025 Wrapped up TA-ing the second offering of MIT’s GPU programming course.
  • Nov 2025 Received the NVIDIA Graduate Fellowship.

Publications

SOSP'24
(Poster)

Using Debug Hardware to Build Tiny and Efficient Dynamic Kernel Checkers

Zachary Yedidia, Akshay Srivastan, Manya Bansal, Dawson Engler

Personal

Before discovering the joys of computer science research, I was interested in philosophy. I represented India at the International Philosophy Olympiad, winning the silver medal. While I read and discuss philosophy much less than I used to, I am more than happy to subject any unlucky ear to my rehearsed spiels.

I also struggle to spell all sorts of words, even ones I use every day, and I spend most of my waking hours listening to music.