Arya Tschand

Computer Science PhD Student at Harvard SEAS.

Hi! I'm Arya, a CS PhD Student at Harvard advised by Vijay Janapa Reddi. My research interests include:

• Hardware-aware language models for kernel optimization
• Intelligence efficiency of multi-agent systems
• Energy efficiency scaling of distributed ML systems

I am currently a Student Researcher at Google (Cloud Research) working on autonomous TPU kernel generation and Gemini developer productivity tools for the TPU software stack.

I am an incoming Research Intern at Nvidia (Architecture Research Group) and will work on autonomous memory localization for Rubin GPUs using hardware-aware code generation.

Previous, I was a Research Intern at AMD (Research & Advanced Development) and worked on enabling hardware-aware language models for memory locality optimizations for MI350 GPU kernels.

Before my PhD, I completed my BSE at Duke majoring in Electrical & Computer Engineering and Computer Science. I was advised by Dan Sorin and worked on statistically rigorous evaluation methods for computer architecture performance and security.

My research is supported by the NSF Graduate Research Fellowship Program (GRFP).

Feel free to contact me at aryatschand@g.harvard.edu!