Andrzej Żurański

Senior Data Scientist - Product

New Jersey, United States
email-iconphone-icongithub-logolinkedin-logotwitter-logostackoverflow-logofacebook-logo
Join Prog.AI to see contacts
email-iconphone-icongithub-logolinkedin-logotwitter-logostackoverflow-logofacebook-logo
Join Prog.AI to see contacts

Summary

👤
Senior
🎓
Top School
Andrzej Żurański is a Senior Data Scientist with a decade of cross-domain experience applying rigorous statistical modeling and machine learning to product and research problems, from CERN particle physics to Google Ads and Assistant. He favors elegant feature engineering and robust validation over flashy algorithms, routinely comparing classical statistical approaches with modern AI and publishing peer-reviewed work from his fellowship at Princeton’s Center for Statistics and Machine Learning. At Google he has driven LLM fine-tuning and win/loss analyses for Assistant and now measures publisher behavior and impact in Ads products, while earlier work delivered major ETA improvements and revenue-grade forecasting for rail clients. Comfortable with production systems and cloud automation (e.g., Auto-QChem for DFT pipelines), he combines experimental design, causal thinking and applied ML to turn messy data into defensible insights.
code10 years of coding experience
job9 years of employment as a software developer
bookMaster's degree Physics, Master's degree Physics at Jagiellonian University
bookDoctor of Philosophy (PhD) Elementary Particle Physics, Doctor of Philosophy (PhD) Elementary Particle Physics at Princeton University
languagesEnglish, Polish, German, French
github-logo-circle

Github Skills (16)

machine-learning10
automation10
dft10
cheminformatics10
python7
data-science7
pytorch7
deep-learning6
tensorflow6
jax5
chemistry5
mutual-information4
materials-informatics3
toolbox3
feature-selection2

Programming languages (3)

C++JavaScriptPython

Github contributions (5)

github-logo-circle
doyle-lab-ucla/auto-qchem

Nov 2019 - Sep 2022

Auto-QChem is an automated workflow for the generation and storage of DFT calculations for organic molecules.
Contributions:1 review, 251 commits, 1 PR in 2 years 10 months
dftcheminformaticsdft-calculationsautomationmachine-learning
Contributions:2 pushes, 1 branch in 5 months
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.
Request Free Trial