Ankur Dave

Experience

UC Berkeley AMPLab	Berkeley, CA
Undergraduate Research Assistant	September 2010 to present

Extending Spark, an open source cluster computing framework, using Scala. Advised by Matei Zaharia and Scott Shenker at the UC Berkeley AMPLab.

Wrote a distributed replay debugger for Spark programs and gave a talk at the AMPLab Winter 2012 retreat (poster, pptx slides, pdf slides)
Used Spark to build Bagel, a Pregel-like distributed graph processing framework, and presented a poster at the AMPLab Summer 2011 retreat
Coauthored a technical report and an NSDI 2012 paper on Spark

Facebook	Palo Alto, CA
Software Engineer Intern	May to August 2011

Added network usage tracking and limit enforcement to Facebook's cluster manager using C++ and Linux cgroups.

Microsoft Research	Redmond, WA
Research Intern	June to August 2010

Built CloudClustering, a scalable clustering algorithm on the Windows Azure cloud, for Microsoft Research's eXtreme Computing Group using C#. Published a workshop paper and gave a talk at DataCloud 2011 (pptx slides, pdf slides).

Jain Foundation	Bellevue, WA
Software Development Consultant	January to June 2010

Improved the Jain Foundation's LAMP-based website.

Berkman Center for Internet and Society at Harvard University	Cambridge, MA
Summer Intern	July to August 2009

Added email alerts to HerdictWeb, a website to collect and analyze reports of Internet censorship, using Java Servlets on Apache Tomcat.

DreamBox Learning	Bellevue, WA
Software Development Engineer Intern	July to August 2007

Created UI components using Adobe Flex, including an abacus and a text-to-speech module, for DreamBox's online education product.

Matei Zaharia, Mosharaf Chowdhury, Tathagata Das, Ankur Dave, Justin Ma, Murphy McCauley, Michael Franklin, Scott Shenker, and Ion Stoica. Resilient Distributed Datasets: A Fault-Tolerant Abstraction for In-Memory Cluster Computing, UC Berkeley Technical Report UCB/EECS-2011-82, July 2011.
Ankur Dave, Wei Lu, Jared Jackson, and Roger Barga. CloudClustering: Toward an iterative data processing pattern on the cloud. In proceedings of the First International Workshop on Data Intensive Computing in the Clouds (DataCloud) 2011.

UC Berkeley	August 2010 to May 2014 (expected)
B.S., Electrical Engineering and Computer Science	GPA: 3.83/4.0

September 2006 to June 2010

Graduated from the Gifted High School Program (PRISM), a highly selective program (99.7 percentile) that groups together gifted students, challenging them with a rigorous curriculum and strict grading standards
Wrote a research paper on distributed genetic algorithms applied to the Boggle word game that was chosen from over 80 others to showcase as an example of excellent work to the faculty of Interlake High School
Led a team of six AP Computer Science students to develop a 3D game for Microsoft's regional Hunt the Wumpus competition
Awards: National AP Scholar, IB Diploma, National Merit Finalist, Rensselaer Polytechnic Institute Medal