Our researchers are driving innovation across the entire hardware, software and network stack to make computer systems more reliable, efficient and secure.
From internet-scale networks, to next-generation chip designs, to deep learning frameworks and more, we build and refine the devices and applications that individuals, industries and, indeed, entire economies depend upon every day.
Research Groups & Labs
Bespoke Silicon Group
The Bespoke Silicon Group aims to bring hardware design to its highest art and rapidly conceive of, design and implement entirely new kinds of hardware faster than has ever been done before.
SAMPL
SAMPL is an interdisciplinary machine learning research group exploring problems across the system stack, including deep learning frameworks, specialized hardware for training and inference, new intermediate representations and more.
Faculty Members
Centers & Initiatives
Society + Technology is a cross-campus, cross-disciplinary initiative and community at the University of Washington that is dedicated to research, teaching and learning focused on the social, societal and justice dimensions of technology.
MEM-C is a NSF Materials Research Science and Engineering Center that integrates materials innovations with theory and computation to advance spin-photonic nanostructures and elastic layered quantum materials, aided by an “AI Core” that integrates artificial intelligence-driven materials discovery.
Highlights
Allen School News
A team of University of Washington and NVIDIA researchers developed FlashInfer, a versatile inference kernel library that can help make large language models faster and more adaptable, and received a Best Paper Award at MLSys 2025 for their work.
Allen School News
Armon Dadgar (B.S., ‘11) co-founded the high-flying cloud company HashiCorp inspired by an undergraduate research project. Now he and partner Joshua Kalla hope to sow the seeds of the next HashiCorp with a new professorship and support for a new generation of innovators and entrepreneurs.
Allen School News
Deeds introduced partition constraints, a new approach for making conjunctive query executions more efficient. He presented the research at the 28th International Conference on Database Theory (ICDT), earning both the Best Student Paper and Best Paper Awards.