Vijay Arya
Senior Researcher at IBM India Research Lab (IRL)
Bengaluru, Karnataka, India
Summary
🤩
Rockstar🎓
Top SchoolVijay Arya is a Senior Researcher based in Bengaluru with over 7 years of professional experience and a PhD in computer science from Université Côte d'Azur/INRIA. He blends deep expertise in AI, machine learning and LLMs with domain knowledge in smart grids, energy systems, and computer network measurement and tomography. At IBM Research he focuses on trusted AI, statistical inference and optimization, translating research into robust tools and methodologies for monitoring and performance modeling. His open-source contributions include practical work on the AIX360 explainability toolkit, improving tutorials, dependency management and SHAP/LIME integration to make model interpretability more accessible. Vijay’s background spans international research labs (INRIA, NICTA) and industry, giving him a rare combination of theoretical rigor and hands-on systems experience. Colleagues rely on him for solving noisy, networked-data inference problems where explainability and reliability matter as much as predictive accuracy.
6 years of coding experience
4 years of employment as a software developer
Indian Institute of Technology Delhi (IIT Delhi)PhD (INRIA Sophia Antipolis), Computer Science, PhD (INRIA Sophia Antipolis), Computer Science at Université Côte d'Azur
English, Hindi, Kannada, French
Stackoverflow
1reputation
0reached
0answers
0questions
Github Skills (17)
shap10
python10
data-science10
scikit10
lime10
explainable-artificial-intelligence10
tensorflow10
scikit-learn10
pandas9
xgboost9
numpy9
machine-learning9
documentation8
artificial-intelligence8
testing8
Programming languages (1)
Github contributions (5)
Trusted-AI/AIX360
Jul 2019 - Nov 2022
Interpretability and explainability of data and machine learning models
Role in this project:
ML Engineer & Data Scientist
ML Engineer & Data ScientistContributions:4 releases, 195 commits, 105 PRs in 3 years 3 months
Contributions summary:Vijay primarily focused on updating and maintaining the AI Explainability 360 (AIX360) toolkit, a library for interpreting machine learning models. Their contributions included updates to documentation, including tutorials and example notebooks. They also specified Tensorflow versioning, added dependencies like Lime and Shap, and made code modifications related to Shap explainer tests and the HELOC use case. Furthermore, the user updated setup.py with various dependencies and configuration settings, indicating involvement in project setup, testing, and the integration of explainability techniques.
explainable-mlibm-research-aitrusted-aicodaitdeep-learning
vijay-arya/AIX360
Oct 2019 - Oct 2019
Interpretability and explainability of data and machine learning models
Contributions:33 pushes in 3 days
fairness-mlinterpretabilitydata-sciencedeep-learningmachine-learning
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.