Hi!
I'm Noah. I'm currently a senior at Brown University studying computer science. I'm interested in
- Compilers and Performance Engineering. I got hooked on coding as a kid from the dopamine hits of learning and the ability to build cool stuff. I think compilers and trying to make things run fast yield some of the most interesting (and useful) technical problems.
- AI and Mechanistic Interpretability. I think it's kind of bonkers that we have powerful models performing sophisticated algorithms yet we only understand a small portion of them. I'm interested in the line of research that aims to charactize model computation and reverse engineer it.
- Cognitive Science. Understanding why humans think and make decisions the way they do has been a perennial interest of mine.
I started a blog recently to think better thoughts and develop stronger opinions.
Other stuff:
- I interned at Netflix over the summer working on automating TV UI navigation using VLMs. For more info on what other stuff I've done in the past, my resume is available.
- I'm using beeminder to keep me accountable to write regularly. You can see my progress here.
- You can reach me at noah_rousell@brown.edu!
Recent Projects
See resume for others
Dimspector: PyTorch Static Shape Inference
A devtool that statically infers the shape of PyTorch tensors to provide inlay hints and catch shape mismatches immediately. Still in development.
Verilog CPU
An 8-bit computer (with accompanying basic assembler) written from the ground up in verilog. Currently in the process of putting this onto an FPGA and hooking up some hardware!
ATA
ATA is a student-facing chatbot that acts as a tutor I built with a few friends for use in Brown courses. Professors drop in their course materials and get course analytics; students can then chat with ATA about lectures and assignments. ATA is university-sanctioned and in use by hundreds of students across multiple courses at Brown. We are lucky to be supported by funding from B* and API credits from OpenAI. ATA was also featured in the 2025 edition of Brown CS's magazine, Conduit.