JOY ARULRAJ

Computer Science Department
Carnegie Mellon University

Office: GHC 8023
Email: jarulraj@cs.cmu.edu
Twitter: @joy_arulraj
Blog: jarulraj
GitHub: jarulraj

Picture

NEWS

I wrote a new blog article on Interstellar database systems.

I had a great time interning at the Microsoft Research Database Group in Fall 2017. I am glad to have had the opportunity to be mentored by Justin Levandoski and Umar Farooq Minhas.

I am grateful to be supported by the Samsung PhD fellowship.

We are building a new self-driving database management system code-named Peloton.

We ported PostgreSQL to C++. This began an interesting conversation on the pgsql-hackers mailing list.

I TA'ed the database systems course in Spring 2016. Here are some interesting student projects from that course. We had a great time.

ABOUT ME

I am a fourth-year PhD student in the Database Group at Carnegie Mellon University. I am advised by Andy Pavlo. I am a member of the Parallel Data Lab.

I earned a M.S. from University of Wisconsin, Madison, where I was fortunate to be advised by Shan Lu. For my B.E., I studied Computer Science and Engineering at College Of Engineering, Guindy under the guidance of Prof. Ranjani Parthasarathi.

I am a member of the Speakers Club. I enjoy playing squash.

RESEARCH INTERESTS

Data Management Systems for Next-Generation Storage Technologies: I explore, design, and build data management systems for next-generation storage technologies. For the first time in 25 years, a new non-volatile memory category is being created that is expected to be 1000 times faster than current durable storage devices. This blurs the gap between memory and storage. My research focuses on understanding the changes required in database systems to leverage the unique characteristics of these technologies.

Data Management Systems with Domain-Specific AI: I am excited about self-driving data management systems with domain-specific AI that enables them to automatically adapt to evolving real-world workloads. I design algorithms for incrementally morphing the storage layout, access methods, and data placement policy employed inside the data management system in tandem with workload shifts.