Prasanna Sattigeri
Principal Research Scientist And Manager at IBM
Greater Boston United States
Summary
🤩
Rockstar🎓
Top SchoolPrasanna Sattigeri is a Principal Research Scientist and manager at IBM Research AI and the MIT-IBM Watson AI Lab, focused on improving the reliability, safety, and governance of large language models and foundation models. With a PhD in Electrical Engineering and over seven years in industry research, he blends theoretical work in generative modeling, uncertainty quantification, and learning from limited data with practical systems and toolkits that push trustworthy AI into production. He has been a key contributor to widely used open-source projects such as AI Fairness 360, AI Explainability 360, and Uncertainty Quantification 360, improving notebooks, documentation, and example workflows to make responsible-AI techniques accessible. Known for bridging deep research and engineering, he leads teams that translate formal guarantees and interpretability methods into scalable solutions deployed across IBM. Based in Greater Boston, he brings a track record of multidisciplinary projects dating back to sensor signal processing and image/sound learning from his doctoral work, giving him unusual depth across both low-level signal methods and high-level LLM governance.
7 years of coding experience
4 years of employment as a software developer
PhD, Electrical Engineering, PhD, Electrical Engineering at Arizona State UniversityBachelor of Technology, Electrical Engineering, Bachelor of Technology, Electrical Engineering at National Institute of Technology
Github Skills (14)
machine-learning10
jupyter-notebook10
f10
n10
ai10
python10
deep-learning8
deeplearning-ai8
r7
pandas6
numpy6
scikit-learn6
scikit6
documentation5
Programming languages (3)
Github contributions (5)
Trusted-AI/AIF360
Sep 2018 - Jun 2020
A comprehensive set of fairness metrics for datasets and machine learning models, explanations for these metrics, and algorithms to mitigate bias in datasets and models.
Role in this project:
Data Scientist
Data ScientistContributions:20 commits, 19 PRs, 14 pushes in 1 year 9 months
Contributions summary:Prasanna primarily contributes to the project by modifying and updating the example notebooks, including commenting on the code, refining the descriptions, and removing unnecessary outputs. They focused on the notebooks related to fairness algorithms, such as adversarial debiasing and learning fair representations. They also performed code cleanup tasks, such as removing redundant files and sample images.
fairness-mlpythondiscriminationbias-reductionfairness-testing
IBM/UQ360
Jun 2021 - Nov 2022
Uncertainty Quantification 360 (UQ360) is an extensible open-source toolkit that can help you estimate, communicate and use uncertainty in machine learning model predictions.
Contributions:14 reviews, 27 commits, 18 PRs in 1 year 5 months
data-sciencecommunicateuncertainty-quantificationcalibrationestimate
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.