About Me
Welcome to my corner of the internet
Hello! I am a researcher passionate about pushing the boundaries of knowledge. I am a Postdoctoral Research Associate at Oak Ridge National Laboratory working at the intersection of AI for Science & Operations, AI system reliability, and hardware-aware machine learning. My research focuses on building robust, trustworthy, and safety-aware AI systems that can be reliably deployed in mission-critical environments.
I believe in open science, collaborative research, and using technology to make the world a better place. When I am not in the lab, you will find me exploring creative outlets and contributing to the community.
Latest Highlights
Education
Academic journey
Ph.D. in Computer Science
The University of Texas at Dallas, Richardson, USA.
Advisor: Dr. Kanad Basu
Thesis: "Functional Safety of Mission-Critical Hardware" - Research focus on Fucntional Safety of deep learning models/accelerators.
M.S. in Electrical & Computer Engineering
North Dakota State University, Fargo, USA
Advisor: Dr. Sumitha George
Thesis: "Exploration of Multi-Threshold Ferro-Electric Field Effect Transistor Based Designs"
B.Tech. in Electrical Engineering
RCC Institute of Information Technology, Kolkata, India
Experience
Work experience
Post-doctoral Research Associate
UT-Battle - Oak Ridge National Laboratory, Oak Ridge, USA.
Enhancing Operational Safety via Agentic Dialogue Hazard Identification Analysis (SIGDIAL’26).
Exploring Agentic orchestration for scientific hypothesis generation, verification and feedback loop for automated scientific discovery.
Graduate Research Assistant
TIES Research Lab, University of Texas at Dallas.
Investigated the vulnerabilities of Lareg Language Models to Adversarial Bit Flipping (TMLR’25).
Devised Fault mitigation in DNNs using uncertainty quantification and multi-exit networks (DAC’24).
Enhanced the Security of DNNs by creating high-quality functional test patterns for detecting attacks (HOST’24).
Investigated the vulnerabilities of Binary Neural Networks to Adversarial Bit Flipping (TMLR’24).
Developed a novel graph learning-based approach for fault criticality analysis in E/E systems (DAC’24, DAC’25).
ORISE Fellow (Internship)
Oak Ridge National Laboratory, Oak Ridge, TN, USA.
Leverage AI techniques, including GenAI and reasoning LLMs, to develop a semi-automated Human-in-the-Loop (HITL) system for high-risk property identification.
Build an agentic AI workflow, towards forecasting hazardous events at DOE sites, conducting risk analysis based on past incidents to enhance safety.
Graduate Research Assistant
North Dakota State University, Fargo, USA
Designed a binary converter using FeFETs, binary, and ternary In-Memory Computing algorithms using QAHE memories.
System Engineering
Tata Consultancy Services, Bhubaneswar, India
Developed tailored IFS application customizations, optimizing using C#, Azure, PL/SQL, and Oracle Database expertise.
Research
Current and past research projects
AI-Driven Scientific Discovery & Hypothesis Generation
Developing novel workflows that leverage state-of-the-art AI tools and foundation models to assist in scientific hypothesis generation. The investigation focuses on building structured, reproducible AI-driven pipelines that augment domain experts in generating testable scientific insights across interdisciplinary research domains.
AI for Workplace Safety in Mission-Critical Environments
Designing intelligent systems that enhance operational safety in mission-critical work sites. This includes risk-aware AI frameworks, structured safety knowledge integration, and automated decision-support systems aimed at reducing hazards and improving situational awareness.
Publications
Selected peer-reviewed works
Enhancing Operational Safety via Agentic Dialogue Hazard Identification Analysis
AttentionBreaker: Adaptive Evolutionary Optimization for Unmasking Vulnerabilities in LLMs through Bit-Flip Attacks,
Bit-by-Bit: Investigating the Vulnerabilities of Binary Neural Networks to Adversarial Bit Flipping
HARNESS: Human-Agent Risk Navigation and Event Safety System for Proactive Hazard Forecasting in High-Risk DOE Environments
“MENDNet: Just-in-time Fault Detection and Mitigation in AI Systems with Uncertainty Quantification and Multi-Exit Networks.
“Explainability to the Rescue: A Pattern-Based Approach for Detecting Adversarial Attacks.
Teaching
Courses & mentorship
DSE 697: Foundations and Applications of Large Language Models
Delivered a graduate-level lecture on foundational concepts of deep learning, convolutional Neural networks, recurrent neural networks and transformer concepts.
CE 6303 — Testing & Testable Design
Mentored graduate student in circuit fault analysis research.
ECE 173 – Introduction to Computing - Lab Instructor
Guided undergraduate students in developing strong foundations in programming. Emphasized clean coding practices, debugging strategies. Provided hands-on mentoring throughout implementation projects.
ECE 375 – Digital Design II - Lab Instructor
Guided undergraduate students in understanding digital systems, and structured design methodology. Discussed verification techniques, and disciplined engineering workflows. Provided hands-on mentoring throughout multi-stage design and implementation.
News
Latest updates & announcements
Reviewed a paper for IEEE Design & Test.
Invited Speaker, Agentic AI Systems Tutorial. CCSD Summer Intern Summit, Oak Ridge National Laboratory (ORNL).
Reviewed a paper for IEEE Transactions on Very Large Scale Integration Systems.
Received Best poster award at 14th ORPA Research Symposium for the work "Intelligent Parameter Space Exploration for Enabling Agentic Cosmological Simulations."
Paper accepted in Results in Engineering Journal
"Accelerating Compact UWB Fractal Antenna Design Using Interpretable Machine Learning with Forward and Inverse Prediction".
Paper accepted in Workshop on Retrieval Augmented Generation for Report Generation(RAG4Reports), ACL 2026
"HARNESS: Human-Agent Risk Navigation and Event Safety System for Proactive Hazard Forecasting in High-Risk DOE Environments".
Paper accepted in Workshop on Retrieval Augmented Generation for Report Generation(RAG4Reports), ACL 2026
"ORCHID: Orchestrated Retrieval-Augmented Classification with Human-in-the-Loop Intelligent Decision-Making for High-Risk Property".
Paper Accepted at premere NLP conference SIGDIAL, 2026
Our paper "Enhancing Operational Safety via Agentic Dialogue Hazard Identification Analysis" has been accepted! Looking forward to presenting this Fall at Atlanta.
Community
Service, outreach & involvement
Volunteer Organizer
Oak Ridge National Laboratory (ORNL) Postdoctoral Association Research Symposium 2026
Conference Reviewer
Regular reviewer for IJCNLP-AACL, ASP-DAC, SOCC, ICPADS, ICCAD, VTS, DAC, DCAS, CVPR, D&T, EACL etc.
Guest Tutor (Grades 5–10)
Volunteered as a tutor in mathematics, physical sciences, and English, supporting students from rural backgrounds in building strong academic foundations and improving access to STEM education.
CE 6303 — Testing & Testable Design
Mentored graduate student in circuit fault analysis research.
Activities
Professional development & engagement
Creative
Beyond the lab — click any card to explore