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 are broadly in co-designing emerging computer architectures with emerging machine learning model architectures. These include

• Efficient ML training and inference on emerging computing architectures
• Hardware-aware language models for kernel optimization
• Energy efficiency scaling of datacenter and edge ML systems

I am an incoming Research Intern at Nvidia (Architecture Research Group) and am working on inference optimizations for sparse attention mechanisms on disaggregated Rubin + LPU systems.

I am currently a Student Researcher at Google Research working on autonomous TPU kernel generation and internal Gemini kernel optimization tools.

Previously, I was a Research Intern at AMD (Research & Advanced Development) and worked on autonomous GPU memory locality kernel optimizations.

Before my PhD, I graduated with distinction from Duke with a double major 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.