Aaron Kramer
Staff Applied Scientist at Uber
Bethesda, Maryland, United States
Summary
🤩
Rockstar🎓
Top SchoolAaron Kramer is a Staff Applied Scientist with a decade of experience building and deploying production machine learning systems, currently leading measurement and optimization efforts at Uber. He has deep expertise in programmatic advertising, causal inference, real-time bidding, and ML infrastructure from senior roles at System1, Clicktripz, and DataScience.com. A core contributor to model-interpretability tooling—having worked on the widely used LIME library and the Skater project—he blends research-grade data science with pragmatic engineering to ship reliable models. He teaches and authors educational resources on NLP and has delivered applied courses for practitioners. Trained in econometrics at Swarthmore, he brings a quantitative, experiment-driven lens to product and marketing problems. Outside work he explores the intersection of technology and food, reflecting a curiosity that informs creative problem solving.
10 years of coding experience
8 years of employment as a software developer
BA Economics, BA Economics at Swarthmore College
French, Hebrew
Github Skills (8)
scikit10
xai10
machine-learning10
explainable-artificial-intelligence10
python10
scikit-learn10
numpy9
regression9
Programming languages (3)
Github contributions (5)
marcotcr/lime
Mar 2017 - May 2017
Lime: Explaining the predictions of any machine learning classifier
Role in this project:
ML Engineer
ML EngineerContributions:23 commits, 3 PRs, 4 comments in 2 months
Contributions summary:Aaron primarily contributed to the `lime` library, which is designed for explaining machine learning models. Their work focused on developing and refining the `lime_tabular.py` module to incorporate explanations for regression models and supporting features. The user also addressed code style issues and implemented support for classifiers that do not output probabilities. Other contributions included fixes related to data discretization and addressing a bug related to the numpy.
predictionsclassifiermachine-learninglime
datascienceinc/lime
Feb 2017 - Aug 2017
Lime: Explaining the predictions of any machine learning classifier
Contributions:26 PRs, 64 pushes, 13 branches in 5 months
predictionsclassifiermachine-learninglime
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.