Skip to content

Software & Hardware Systems

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

Stacked rocks in a beach scene

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.

Database Group cover image of a mountain

Database Group

The Database Group advances both theoretical and systems work in probabilistic databases, stream processing, sensor-based monitoring, databases and the web, XML, image/video data management, data management for machine learning, data mining and more.


Faculty Members

Faculty


Centers & Initiatives

IFDS organizes its research around four core themes: complexity, robustness, closed-loop data science, and ethics and algorithms. By making concerted progress on these fundamental fronts, IFDS aims to lower several of the barriers to better understanding of data science methodology and to its improved effectiveness and wider relevance to application areas.

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.

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.