Scott Lundberg
Member Of Technical Staff at Microsoft AI
Seattle, Washington, United States
Summary
🤩
Rockstar🎓
Top SchoolScott Lundberg is a Member of Technical Staff at Microsoft AI and a former Staff Research Scientist at Google DeepMind with 11 years of professional experience focused on language models, explainable AI, and applying these tools to medicine, healthcare, and finance. He builds broadly applicable methods and tooling for interpreting complex ML models and has contributed to notable open-source projects—improving benchmarks and visualizations in SHAP, adding backend and DevOps integrations to the guidance language, and enhancing Mocha.jl’s documentation and error reporting. With a PhD from the University of Washington and a background spanning signal processing, graph-theoretic algorithms, and an entrepreneurial stint running a web-hosting/tools company, he blends rigorous research with production engineering. Colleagues rely on him to translate theoretical insights into usable systems, often by shipping clearer tutorials, better diagnostics, and cross-stack fixes that make complex models more trustworthy and deployable.
11 years of coding experience
11 years of employment as a software developer
University of WashingtonBachelor of Science (B.S.), Computer Science, summa cum laude, Bachelor of Science (B.S.), Computer Science, summa cum laude at Colorado State UniversityAssociate of Arts (A.A.), Associate of Arts (A.A.) at Aims Community College
Github Skills (25)
javascript10
documentations10
python10
scikit10
machine-learning10
deep-learning10
javascripts10
scikit-learn10
julia10
documentation10
data-analysis10
testing9
debug9
maintenance9
debugging9
Programming languages (9)
Github contributions (5)
shap/shap
Nov 2016 - Nov 2022
A game theoretic approach to explain the output of any machine learning model.
Role in this project:
Data Scientist
Data ScientistContributions:44 releases, 29 reviews, 1311 commits in 6 years 1 month
Contributions summary:Scott's commits focused on updating and improving the benchmark measures within the shap/shap repository. These changes involved updating benchmark updates by modifying the measures.py file, and also creating new files with improved visualizations and tests. These changes would impact the models that use standardized features.
explaininterpretabilityshapdeep-learningapproach
guidance-ai/guidance
Dec 2022 - Aug 2024
A guidance language for controlling large language models.
Role in this project:Back-end Developer & DevOps Engineer
Back-end Developer & DevOps EngineerContributions:30 releases, 7 reviews, 106 PRs in 1 year 8 months
Contributions summary:Scott implemented significant changes in the coding and notebooks directories, indicating contributions to both the backend logic and related processes within the guidance repository. Their work involved merging main branches, fixing bugs, and adding tests, with changes to files like _prompt.py and prompt-display.js. They demonstrated proficiency in code cleanup, including adding JS code, which suggests a focus on both code functionality and integration with the frontend components.
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.