Shvetank’s research aims to realize AI agents and ML methodologies that automate and accelerate the design of next-generation hardware architectures. To this end, his current work focuses on developing datasets, benchmarks, and algorithms used to train and evaluate the foundation models powering such agents for computer architecture tasks. His broader research also explores hardware-software co-design and emerging technologies for ultra-low power machine learning systems at the Edge.
Shvetank Prakash is a fifth-year Ph.D. candidate in computer science at Harvard University, advised by Prof. Vijay Janapa Reddi. He received his B.S. in computer engineering from Columbia University in 2021. His professional experience includes internships at NVIDIA, Google, Pragmatic Semiconductor, and Amazon. He was recently named a 2026 ML and Systems Rising Star by MLCommons.