I find computer networks intriguing and have been studying, building and operating them since 2016. I currently work as a Research Scientist at Meta, where I am part of an awesome team in charge of a hyperscale AI infra network. I obtained Ph.D. from University of Washington, where I was fortunate to work with Ratul Mahajan and Arvind Krishnamurthy to advance the state of the art of network verification. Prior to that, I got my B.S. from Peking University. I was introduced into the area of computer networks by my undergraduate advisor Chenren Xu.
Research Highlights
My PhD dissertation aims to remedy the reliability risks in the day-to-day operation of network infrastructure. It pineers the use of coverage metrics in network testing [1] [2] and develops a formal language to describe real-world network changes in just a few lines [3]. Such research findings enabled a new paradigm of network operation, in which engineers can afford to handcraft a precise specification of desired operation steps (previously this is too slow and error-prone to be performed by human engineers), and rigorously test/verify them before rolling out.
A significant portion of this research is building production-ready systems, running them in some of the world’s most hyperscale networks and pushing them to (early-stage) adoption [1] [3]. Network operation is a field dominated by the fear of instability—new technologies will only be adopted if the risks and costs to adapt can be justified by huge benefits. Establishing early-stage adoption is a positive signal!
My research [2] has also won an Applied Networking Research Prize from IRTF (Internet Research Task Force) [4].
Publications
See this page for publication details.
Contact
[first name] at [uw] dot [edu]