Amit Dhurandhar
Principal Research Staff Member And Explainable AI Strategic Lead
Town of Yorktown, New York, United States
Summary
🤩
Rockstar🎓
Top SchoolAmit Dhurandhar is a Principal Research Staff Member and Explainable AI strategic lead at IBM TJ Watson with over a decade of experience in machine learning and AI research. He holds a PhD in Machine Learning/Data Mining from the University of Florida and has led development of practical interpretability tools, contributing key algorithms and tutorials to the open-source AI Explainability 360 (AIX360) toolkit. Known for blending deep technical rigor with clear communication, he focuses on making complex models auditable and trustworthy for real-world use. Based in Yorktown, NY, he also brings uncommon entrepreneurial grit—co-running a local Indian food stall—which reflects his curiosity and hands-on problem-solving beyond academia.
10 years of coding experience
1 year of employment as a software developer
BE, Computer Engineering, BE, Computer Engineering at Pune UniversityPhD, Machine Learning/Data Mining, PhD, Machine Learning/Data Mining at University of Florida
Github Skills (13)
xai10
machine-learning10
explainable-artificial-intelligence10
python10
data-analysis10
scikit-learn9
tensorflow9
scikit9
deep-learning9
nlp7
natural-language-processing7
computer-vision7
pandas7
Programming languages (2)
Github contributions (4)
Trusted-AI/AIX360
Aug 2019 - Oct 2022
Interpretability and explainability of data and machine learning models
Role in this project:
ML Engineer & Data Scientist
ML Engineer & Data ScientistContributions:15 commits, 7 PRs, 1 push in 3 years 2 months
Contributions summary:Amit primarily contributed to the AI Explainability 360 toolkit, focusing on algorithms and tutorials related to model interpretability. Their work involved updating and modifying code for various explainers, including CEM, ProtoDash, and ProfWeight. They also updated documentation and tutorials demonstrating the application of these explainers on datasets like CDC and HELOC.
explainable-mlibm-research-aitrusted-aicodaitdeep-learning
sadhamanus/AIX360
Aug 2019 - Feb 2025
Open Source library to support interpretability and explainability of data and machine learning models
Contributions:16 pushes in 5 years 6 months
interpretabilitydata-sciencemachine-learningattributionopenscience
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.