I am currently pursuing my Ph.D. in Computer Science at Virginia Tech. Broadly I am interested in machine learning, natural language processing, and computational social science. More specifically, I am working on out-of-distribution detection, and contrastive learning.

Before starting my graduate studies, I completed my undergrad at the University of Dhaka. I have prior experience working as a Full Stack Web Developer at Enosis Solutions. More recently, I have worked as a Machine Learning Engineer (R&D) at TigerIT Bangladesh Ltd., where I have worked with signal processing and video classification. I have also worked as a Research Assistant at Data & Design Lab, where I have worked with Satellite data to design socio-economic proxies. While working at Data & Design Lab I have also collaborated with BRAC on UID generation project, COVID-19 data analysis, and the development of a web portal for economic data analysis.

I have a fairly good understanding of statistical concepts and machine learning, and a broad experience with programming language and frameworks, especially Python and C. Additionally, I have experience working with Android and Full Stack Web Development. A combination of these skills makes me a strong candidate for R&D jobs, where prototype development is as important as researching new frontiers.

News

• August, 2021: My paper on truncated sparse bit-vector representations was accepted to CIKM’21 Applied Track (joint work with IBM Research).
• February, 2021: Started working with Dr. Ismini Lourentzou.
• January, 2021: Joined Virginia Tech as a Ph.D. Student in Computer Science.
• December, 2020: Left TigerIT Bangladesh Limited
• June, 2020: Joined TigerIT Bangladesh Limited as a Machine Learning Software Engineer
• June, 2020: Left Data & Design Lab
• October, 2019: Left Enosis Solutions.
• April, 2019: Joined Enosis Solutions as a Software Engineer, and Data and Design Lab as a Research Assistant.
• January, 2019: Completed my B.Sc. in Computer Science and Engineering from the University of Dhaka.