About me
About
Graph algorithms, scalable learning, and AI systems for scientific and applied domains.
I am a Postdoctoral Researcher at Pacific Northwest National Laboratory (PNNL), in the Language Intelligence group within the Data Science and Machine Intelligence department. I work at the intersection of graph algorithms, machine learning, and scalable AI systems.
My research develops graph neural networks and sparsification methods for large, complex graphs, including homophilic and heterophilic networks. I also study learning for hardware/software partitioning, scheduling, circuit representation, and equivalence checking.
At PNNL, I build LLM-based, multimodal, and agentic systems for document intelligence, retrieval-augmented generation, georeferencing, and decision support. My cybersecurity research connects software vulnerabilities, weaknesses, and attack patterns through language models and knowledge graphs.
I received my Ph.D. in Computer Science from Purdue University in May 2025, advised by Alex Pothen. I earned my M.Sc. and B.Sc. in Computer Science and Engineering at BUET, advised by Md. Monirul Islam, and previously served as a Lecturer and Assistant Professor in BUET’s CSE department.
During three summer internships at PNNL (2019–2021), I worked with Mahantesh Halappanavar on language models for vulnerability analysis. This work received the DSAA 2021 Best Application Paper Award and the HST 2022 Best Paper Award.
Research interests
Research experience
Postdoctoral Researcher, Data Science & Machine Intelligence
Pacific Northwest National Laboratory (PNNL), Richland, WA, USA · May 2025 – Present
Conducts research in AI, machine learning, graph algorithms, and system design, with a focus on scalable GNN-based methods for hardware/software partitioning, scheduling, graph partitioning, and graph sparsification. Develops LLM-based, multimodal, and agentic AI systems for scientific and applied applications, including large-scale processing of environmental and regulatory documents (metadata extraction, georeferencing, project summarization, RAG, and interactive decision support).
Graduate Research Assistant
Department of Computer Science, Purdue University, West Lafayette, IN, USA · Aug 2018 – May 2025
Researched scalable graph learning, graph sparsification, and machine learning on large graphs, along with LLM-based methods for software vulnerability analysis and cyber threat understanding. Developed new sampling and sparsification methods for GNNs, leading to publications at KDD, DSAA, Big Data, and HST.
Ph.D. Intern, Data Analytics
Pacific Northwest National Laboratory (PNNL), Richland, WA, USA · Summers 2019 – 2021
Mentored by Mahantesh Halappanavar. Developed learning-based methods for classification and analysis of software vulnerabilities, including mapping CVEs to weaknesses (CWEs) and attack patterns (CAPECs), using LLMs and NLP scaled for modern AI accelerators. Published four papers during the internship, including two best paper awards.
Assistant Professor, Department of Computer Science and Engineering
Bangladesh University of Engineering and Technology (BUET), Dhaka, Bangladesh · Dec 2017 – Jul 2018
University teaching, project supervision, and administration. On study leave for the Ph.D. from July 2018 to July 2024.
Lecturer, Department of Computer Science and Engineering
Bangladesh University of Engineering and Technology (BUET), Dhaka, Bangladesh · Aug 2014 – Dec 2017
University teaching.
Education
Ph.D. in Computer Science
Purdue University, West Lafayette, IN, USA · Aug 2018 – May 2025
Advisor: Alex Pothen. Thesis: "Scaling Graph Neural Networks for Large Graphs and Analyzing Common Vulnerabilities via Large Language Models." Topics: machine learning on graphs, graph neural networks, cybersecurity, large language models.
M.Sc. in Computer Science and Engineering
Bangladesh University of Engineering and Technology (BUET), Dhaka, Bangladesh · Sep 2017
GPA: 4.00/4.00. Advisor: Md. Monirul Islam. Thesis: "Evolutionary Algorithm Using Adaptive Fuzzy Dominance and Reference Point for Many-Objective Optimization (F-DEA)."
B.Sc. in Computer Science and Engineering
Bangladesh University of Engineering and Technology (BUET), Dhaka, Bangladesh · Jul 2014
GPA: 3.88/4.00 (Major: 3.99/4.00). Advisor: Md. Monirul Islam. Thesis: "A Many-objective Evolutionary Approach Using Fuzzy Dominance with Bidirectional Bias."
Teaching experience
Graduate Research Assistant
Purdue University, Department of Computer Science · Aug 2018 – May 2019
Courses: Algorithms, Data Structures, and others.
Assistant Professor / Lecturer
Bangladesh University of Engineering and Technology (BUET), Department of Computer Science and Engineering · Aug 2014 – Jul 2018
Courses: Machine Learning, Artificial Intelligence, Computer Graphics, Data Communication, and others.
Honors and awards
Best Paper Award
IEEE HST 2022
"Towards Automatic Mapping of Vulnerabilities to Attack Patterns Using Large Language Models."
Best Application Paper Award
IEEE DSAA 2021
"V2W-BERT: A Framework for Effective Hierarchical Multiclass Classification of Software Vulnerabilities."
Dean's Honor List
BUET, 2011 – 2014
University Merit Scholarship
BUET
Academic service
Reviewer: ICML 2025, KDD 2024, DSAA 2023, The Web Conference (formerly WWW), IEEE Transactions on Artificial Intelligence, and others.
Organizing member: NSysS 2015, 2016, 2017.