I am a computer scientist interested to learn and build beautiful and intelligent systems.
I have graduate school level academical training in computer science (CS) combined with nearly 4 years of software development experience in startups and research labs.
I have the passion for solving problems in the domains of distributed computing, information retrieval, machine learning and applied natural language processing.
I am currently a graduate student pursuing Mater of Science (MS) in CS at the University of Southern California (USC), Los Angeles. Here I worked closely with Dr. Chris Mattmann at the Information Retrieval and Data Science (IRDS) group.
I went to NASA Jet Propulsion Lab for internship (Summer and Fall 2016 ) and worked on Machine Learning and Information Retrieval challenges. I support open source technologies and I am a member of the Apache Software Foundation. Previously, I worked as a full-stack developer in a startup called SimplyPhi Software Solutions , Bangalore, India for three years. I am also a technical co-founder of a startup called Datoin, where I prototyped and deployed a distributed text analytics platform before coming to Grad school.
Events / Conferences / Workshopstwitter feed may be best place!
- Coming up: Feb 07-09, 2017, Boston, MA. Sparkler talk has been scheduled for Spark Summit East 2017
- Nov 29-Dec02, 2016: Darpa Memex Fall16 Workshop, Washington DC.
- Nov 13-15, 2016: Apache Big Data EU, 2016, Seville, Spain. Presented Sparkler : A web Crawler on Spark . Slides are here
- Nov 09, 2016: I was invited to attend IBM Watson Developer conference, in San Fransisco. Edit: I got a job offer as a follow up (Cognitive Software Engineer)!
- Nov 03-04, 2016: Visited Stanford University and the Stanford Info Lab as a guest. Previously I was wishing to visit that campus atleast as a tourist!
- Aug 01-05, 2016: Participated in DARPA MEMEX Summer workshop of this year at Washington DC. Built a binary classifier for classifying cluster of web pages related to human trafficking domain. This model had the best score of all, about 81%, on evaluation dataset; the next best model had 65%. Link to code
- Jul 28-30, 2016: My paper has been accepted by IEEE IRI2016, Pittsburgh, PA . Link to slides - Clustering Web Pages based on Structure and Style Similarity. I visted CMU that weekend as a tourist!
- May 12, 2016: Attended ApacheCon 2016 North America, Vancouver, BC, Canada and presented our Auto Extractor. Link to slides - Clustering output of Apache Nutch using Apache Spark
- Feb 26, 2016: Participated in HackTech @ Caltech, Pasadena, CA. We built USA presidential election (2016) trend analysis tool from twitter data in 36 hour hackathon.
- Feb 22, 2016: Attended The 9th ACM International Conference on Web Search and Data Mining in San Fransisco, CA.
I spent 75 Earth days with rocket scientists and the Explorers at NASA Jet Propulsion Lab, Pasadena, CA , as a Research Intern.