I am a Ph.D. student in Computer Science at the University of Illinois Urbana-Champaign, advised by Dr. Ismini Lourentzou. My research focuses on trustworthy and multi-modal machine learning, with interests in vision-language models, grounded response generation, and conversational AI. I specialize in building robust AI models that can handle missing information, mitigate adversarial attacks, and defend against harmful or malicious content.

Previously, I earned my M.S. in Computer Science from Virginia Tech and my B.Sc. in Computer Science & Engineering from the University of Dhaka. I interned at IBM Research (Almaden Lab) in the summers of ‘22, ‘23, and ‘24, contributing to projects on LLM evaluation, sensitive personally identifiable information (PII) detection, ontology construction, and human-in-the-loop learning, resulting in a conference paper and two patents (one filed, one pending).

I am currently co-leading a team in the Amazon Trusted AI Challenge, where we are developing code generation models that produce secure, non-vulnerable code and are robust against malicious prompts. Additionally, I was part of a finalist team in the Amazon Alexa Prize TaskBot Challenge 2, where my work included task-oriented conversational AI, dynamic caching, harmful content filtering, and intent classification.

My industry experience includes roles as a Machine Learning Engineer at TigerIT Bangladesh Ltd., where I worked on video classification and signal processing, and as a Full Stack Developer at Enosis Solutions. As a Research Assistant at the Data & Design Lab, I collaborated on socio-economic modeling using satellite data and developed data-driven tools for BRAC. My expertise spans deep learning, large language models, and robust ML, with strong programming skills in Python, C, and full-stack development.

News

• May, 2024: Started my internship at IBM Research.
• October, 2023: My paper on multi-modal representation learning for image-to-text and text-to-image retrieval got accepted at the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV).
• August, 2023: Our team advanced to the finals of the Amazon Alexa Prize Taskbot Challenge 2.
• August, 2023: My paper on human-in-the-loop model selection for set expansion got accepted at the 32nd ACM International Conference on Information and Knowledge Management (CIKM).
• May, 2023: Started my internship at IBM Research.
• May, 2023: I completed my M.S. in Computer Science from Virginia Tech.
• March, 2023: Our paper got accepted in Science.
• January, 2023: Our team was selected to participate in Alexa Prize TaskBot Challenge 2.
• December, 2022: I was awarded the Pratt Fellowship by the Department of Computer Science at Virginia Tech.
• October, 2022: My paper on Privacy-Preserving Data Sharing Framework was accepted to IEEE BigData 2022.
• May, 2022: Started my internship at IBM Research.
• August, 2021: My paper on truncated sparse bit-vector representations was accepted to CIKM’21 Applied Track (joint work with IBM Research).
• 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.