I work on the intersection of Artificial Intelligence and Software Systems. My research concentration is Machine Learning for software reliability. Over the years, I developed tools for program comprehension, vulnerability detection, and modeling program changes. My dissertation's primary focus is on improving the software development pipeline(i.e., building better developer assisting tools) with Machine Learning and Deep Learning. I am interested in work problems where I can apply the knowledge I gained throughout my Ph.D. career as well as learn new things to embrace new challenges.
- Passes the Ph.D. candidacy exam. The abstract of the candidacy can be found here
- CODIT got accepted at IEEE Transaction of Software Engineering.
- Deep Learning based Vulnerability Detection: Are We There Yet?, Saikat Chakraborty, Rahul Krishna, Yangruibo Ding, Baishakhi Ray, arXiv pre-print 2020
- CODIT: Code Editing with Tree-Based Neural Models, Saikat Chakraborty, Yangruibo Ding, Miltiadis Allamanis, Baishakhi Ray, TSE, 2020.
- A Transformer-based Approach for Source Code Summarization, Wasi Ahmad, Saikat Chakraborty, Baishakhi Ray, Kai-Wei Change, ACL 2020.
- Building Language Models for Text with Named Entities , Rizwan Parvez,Saikat Chakraborty,Baishakhi Ray, Kai-wei Chang, accepted to be published in 56th Annual Meeting of the Associationfor Computational Linguistics (ACL)’18.
- A Heuristic Initialized Stochastic Memetic Algorithm for MDPVRP With Interdependent Depot Operations, AS Azad, MM Islam, S Chakraborty. IEEE Transactions on Cybernetics, 2017.
Google LLC.Sunnyvale, CA
May 2019 - August 2019
Worked in designing ML based tool for analyzing security and privacy.
Fujitsu Laboratories of AmericaSunnyvale, CA
May 2017 - August 2017
Supervisor : Dr. Ripon K Saha
Worked with AI based program repair tool. Extracted subtle information from auxiliary sources to improve the performance of fault localization and program repair.
Stochastic Logic Ltd Dhaka, Bangladesh
July 2015 - August 2016
Quantitative Software Developer
Supervisor : Dr. Arif Dowla
Designed a robust model to estimate Value-at-risk(VAR) from stock market data. Also developed a intelligent model to manage stock portfolio.
Ahsanullah University of Science and TechnologyDhaka, Bangladesh
October 2014 - August 2016
Taught undergraduate course on digital system design and compiler. Supervised undergrad research project.
Kona Software Lab Ltd.Dhaka, Bangladesh
June 2014 - October 2014
Jr. Software Engineer
Designed Proof of Concept of Host Card Emulation System with VISA based payment networks.
Software Tools/Scripting Languages