Embedded Files
Siddhartha Shankar Das
Graph learning. Scalable AI. Scientific impact.
Graph learning. Scalable AI. Scientific impact.
Postdoctoral Researcher · Pacific Northwest National Laboratory
Language Intelligence group · Data Science & Machine Intelligence
I develop graph learning algorithms and AI systems that turn complex, connected data into useful scientific and engineering decisions. My research spans graph neural networks, graph sparsification, learning for system design, cybersecurity, and multimodal document intelligence.
I received my Ph.D. in Computer Science from Purdue University in May 2025, advised by Alex Pothen, and my M.Sc. and B.Sc. in Computer Science and Engineering from BUET, advised by Md. Monirul Islam. I previously served as a Lecturer and Assistant Professor at BUET; I was on study leave for my Ph.D. from July 2018 to July 2024.
At PNNL, I study scalable graph learning, hardware/software partitioning and scheduling, circuit representation, and LLM-based systems for retrieval, metadata extraction, georeferencing, and decision support. My work has received the DSAA 2021 Best Application Paper Award and the HST 2022 Best Paper Award.
Research website · CV — October 2026 · Google Scholar · GitHub · LinkedIn · PNNL profile
siddhartha.das@pnnl.gov
Updated October 2026
I grew up in Bagerhat in southwestern Bangladesh, near the Sundarbans.
Current appointment
Current appointment
Postdoctoral Researcher, Pacific Northwest National Laboratory
May 2025–present
Language Intelligence group, Data Science & Machine Intelligence.
Education
Education
Ph.D. in Computer Science — Purdue University
August 2018–May 2025. Advisor: Alex Pothen.
Dissertation: Scaling Graph Neural Networks for Large Graphs and Analyzing Common Vulnerabilities via Large Language Models.
M.Sc. in Computer Science and Engineering — BUET
September 2017. Advisor: Md. Monirul Islam. GPA: 4.00/4.00.
B.Sc. in Computer Science and Engineering — BUET
July 2014. Advisor: Md. Monirul Islam. GPA: 3.88/4.00.
Teaching, mentoring & service
Teaching, mentoring & service
At PNNL, I mentored five interns from August 2025 to May 2026 on graph neural networks, circuit representation learning, and cybersecurity, contributing to three accepted publications.
I taught at Purdue (August 2018–May 2019) and BUET (August 2014–July 2018). My teaching spans algorithms, data structures, machine learning, artificial intelligence, computer graphics, and data communication.
Reviewer for ICML 2025, KDD 2024, DSAA 2023, The Web Conference, IEEE Transactions on Artificial Intelligence, and other venues. Organizing member, NSysS 2015–2017.
Earlier education records
Earlier education records
Awards & academic service
Awards & academic service
Best Application Paper Award — IEEE DSAA 2021
V2W-BERT: hierarchical classification of software vulnerabilities.
Best Paper Award — IEEE HST 2022
Automatic mapping of vulnerabilities to attack patterns using large language models.
Dean’s Honor List, BUET (2011–2014); University Merit Scholarship, BUET.
Reviewer: ICML 2025, KDD 2024, DSAA 2023, The Web Conference, IEEE Transactions on Artificial Intelligence, and other venues. Organizing member: NSysS 2015, 2016, and 2017.
Google Sites
Report abuse