Kunal Mukherjee
Postdoctoral Associate
Blacksburg, Virginia, United States
Summary
👤
Senior🎓
Top SchoolKunal Mukherjee is an applied scientist with nine years of experience building and deploying trustworthy, explainable ML systems that power large-scale personalization and security applications. He combines a strong academic foundation in graph-structured data, provenance, and adversarial robustness (PhD + postdoc) with hands-on production work at Zillow, designing ranking and recommendation models that blend behavioral, contextual, and graph-based signals. Kunal has contributed explainable GNN techniques to the widely used Deep Graph Library (DGL), adapting SubgraphX and PGExplainer for heterogeneous graphs, and he brings that open-source XAI experience to production recommender pipelines. His research spans explainable recommenders, interpretable GNNs, privacy-preserving ML, and LLM-powered reasoning for security-critical domains—an unusual mix that helps translate cutting-edge science into measurable product impact. Based in Blacksburg, he is equally comfortable publishing top-tier research and shipping scalable, user-centered systems.
8 years of coding experience
7 years of employment as a software developer
Doctor of Philosophy - PhD, Computer Science, A, Doctor of Philosophy - PhD, Computer Science, A at The University of Texas at DallasBachelor of Science (B.S.), Computer Engineering, A, Bachelor of Science (B.S.), Computer Engineering, A at University of Evansville
English, Hindi, Bengali, Spanish
Github Skills (12)
pytorch10
xai10
explainable-artificial-intelligence10
deep-learning10
graph-neural-network10
python10
testing9
data-structure9
machine-learning9
algorithm9
data-structures9
algorithms9
Programming languages (5)
Github contributions (5)
dmlc/dgl
Sep 2022 - Sep 2023
Python package built to ease deep learning on graph, on top of existing DL frameworks.
Role in this project:
ML Engineer
ML EngineerContributions:133 reviews, 11 PRs, 162 comments in 1 year
Contributions summary:Kunal contributed significantly to the implementation and enhancement of explainable AI (XAI) techniques within the DGL (Deep Graph Library) framework. They focused on developing and refining SubgraphX and PGExplainer, contributing code for both homogeneous and heterogeneous graph explainers. Their work involved adapting existing XAI methods to the DGL environment, addressing deprecated functionalities, and improving testing procedures.
pytorchpythondeep-learningmachine-learninggraph-neural-networks
kunmukh/Interesting-Projects
Aug 2019 - Dec 2021
Contributions:133 commits, 128 pushes, 1 branch in 2 years 4 months
Find and Hire Top DevelopersWe’ve analyzed the programming source code of over 60 million software developers on GitHub and scored them by 50,000 skills. Sign-up on Prog,AI to search for software developers.