Rohan Kadekodi
Postdoctoral Researcher at University of Washington
Pune, Maharashtra, India
Summary
👤
Senior🎓
Top SchoolRohan Kadekodi is a postdoctoral researcher at the University of Washington’s Paul G. Allen School with 11 years of experience building high-performance systems for modern storage and heterogeneous memory technologies. He specializes in extracting peak performance from CXL-attached memory, GPU memory, and byte-addressable storage to accelerate datacenter and machine learning workloads, building on a PhD from UT Austin where he developed novel persistent memory file systems and key-value stores. His work blends rigorous academic research with practical systems engineering—evident from internships at VMware Research and UW–Madison where he built user-space libraries and ported applications for persistent memory. Based in Pune, India, Rohan pairs deep low-level expertise with a track record of shipping performant prototypes that bridge new hardware capabilities and real-world applications.
11 years of coding experience
Graduate Studies, Computer Science, Graduate Studies, Computer Science at The University of Texas at AustinBachelor of Engineering (B.E.), Information Technology, Bachelor of Engineering (B.E.), Information Technology at Pune Institute of Computer TechnologyDr Kalmadi Shamarao High SchoolMarathwada Mitramandal's Junior College of Science and Commerce
English, Marathi, Hindi, Gujarati
Github Skills (53)
filesystem10
memory-allocation10
fat10
ram10
vfs10
prebuild10
persistent10
overhead10
persistent-memory10
in-memory9
nfs9
rdma9
libc9
io-uring9
multicore9
Programming languages (6)
Github contributions (5)
rohankadekodi/rocksdb_mmap
Feb 2020 - Oct 2024
Contributions:4 pushes, 5 branches in 4 years 9 months
utsaslab/SplitFS
Sep 2019 - Dec 2021
SplitFS: persistent-memory file system that reduces software overhead (SOSP 2019)
Contributions:52 commits, 9 PRs, 69 pushes in 2 years 3 months
memorylibcpersistentfile-systempersistent-storage
Find and Hire Top DevelopersWe’ve analyzed the programming source code of over 60 million software developers on GitHub and scored them by 50,000 skills. Sign-up on Prog,AI to search for software developers.