Harsha Nori
Senior Director, Health AI at Microsoft AI
London, England, United Kingdom
Summary
🤩
Rockstar🎓
Top SchoolHarsha Nori is a senior technology leader with 11 years of experience building and operationalizing AI at Microsoft, now leading Health AI within Microsoft AI to improve consumer healthcare outcomes. He blends research engineering, product, and UX collaboration to make AI systems more responsible and practical in real-world health settings. Previously he led interdisciplinary research engineering teams focused on responsible AI, and has hands-on experience from senior data scientist to director roles. An active open-source contributor, he implemented differential privacy features for Explainable Boosting Machines in the popular interpretml project, bringing privacy-preserving techniques into explainable models. Based in London, he combines deep technical breadth from his ECE training at Georgia Tech with a pragmatic focus on deployable, auditable AI systems.
11 years of coding experience
10 years of employment as a software developer
Bachelor of Science - BS Electrical and Computer Engineering, Bachelor of Science - BS Electrical and Computer Engineering at Georgia Institute of TechnologyMICDS
Stackoverflow
68reputation
2kreached
1answer
4questions
Github Skills (16)
scikit-learn10
xai10
machine-learning10
jupyter-notebook10
explainable-artificial-intelligence10
differential-privacy10
python10
scikit10
numpy9
documentation9
ai9
data-analysis8
caching6
excel6
bokeh6
Programming languages (4)
Github contributions (5)
guidance-ai/guidance
Apr 2023 - Mar 2025
A guidance language for controlling large language models.
Role in this project:
Full-stack Developer
Full-stack DeveloperContributions:9 releases, 123 reviews, 75 PRs in 1 year 11 months
Contributions summary:Harsha updated URLs within the project's documentation and example notebooks, aligning them with the new project organization. The user's contributions primarily involved modifying notebook files, specifically in the context of the "guidance" library. These updates included changes to documentation and examples to reflect changes in the project structure.
interpretml/interpret
Oct 2020 - Jul 2022
Fit interpretable models. Explain blackbox machine learning.
Role in this project:ML Engineer
ML EngineerContributions:13 commits, 18 pushes, 2 branches in 1 year 9 months
Contributions summary:Harsha primarily focused on implementing and refining differential privacy (DP) features within the Explainable Boosting Machines (EBM) framework. They added utilities for calculating DP noise, integrated private binning options, and integrated differentially private training methods for EBMs. Their contributions included refactoring privacy logic, adding tests for private classification and regression, and exposing privacy schema customization. The user's work directly enhances the EBM's capabilities for privacy-preserving machine learning.
xaiinterpretmlfitinterpretableexplainability
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.