Pronoy Das
Aspiring AI Safety Researcher · Computational Physicist · ECE PhD Candidate, Purdue University
I am a computational and theoretical physics PhD candidate at Purdue, switching my career direction towards AI safety. I am currently working on the interpretability of models during the RL training process. Previously, I worked on physics problems realted to quantum optics + field theory. I have also worked on optical computing hardware at Sandia National Laboratories, and GPU (CUDA) based high-performance computing pipelines for scientific simulations and imaging.
What I do
Model internals during RLVR
As a part of the BlueDot Impact's AI project, I studied misalignment during RLVR training over intermediate checkpoints. I discovered that RLVR broadly introduceds self-doubt in the model's behavior, rather than behavioral misalignment (read the article in the 'Articles' section).
Computing with physical systems
With Zetascope, I developed dedicated algorithms and corresponding CUDA C++ kernels for near real-time faint-object detection pipelines.
Quantum theory
I developed the quantum theory of light-matter interaction in chiral crystals, and of the angular momentum of structured light, leading to several journal articles, including a Phys. Rev. B Letter (Editor's Suggestion). I also co-authored Purdue-PicoMax, a C++ electromagnetic simulation package built for the theory.
Selected publications
-
Quantum Theory of Optical Spin Texture in Chiral Tellurium Lattice Letter · Editor's Suggestion
-
Quantum theory of orbital angular momentum in spatiotemporal optical vortices Most-read, Aug–Sep 2024
-
What are the quantum commutation relations for the total angular momentum of light? Most-downloaded, Jul–Sep 2024
Awards
- Hugh W. & Edna M. Donnan Dissertation Fellowship2026 Purdue University, for excellence in research
- APS Distinguished Student Award2025 APS Forum on International Physics, APS Global Physics Summit
- Purdue ECE Bravo Award2024 For excellence in teaching as a graduate course instructor
- Purdue Summer Research Grant2024 Competitive university-wide research grant
Contact
The best way to reach me is by email. I read both inboxes daily, and I reply quickly to recruiting and collaboration inquiries.