Summary
Joshua Loyal is a data scientist and PhD-trained statistician who applies experimental particle physics rigor to predictive modeling and large-scale data problems. With 11 years of experience, he has analyzed ~100 TB datasets at institutions including CERN and Argonne and currently develops production analytics at DataRobot while teaching statistics at UIUC. He builds end-to-end tools in Python and C++ (ROOT, TMVA, scikit-learn) and has led projects that improved signal classification using deep learning and ensemble methods. His work blends scientific publication-grade inference—one paper cited by multiple later studies—with practical engineering: recovering corrupted data, running Linux batch analyses, and maintaining collaborative codebases. Known for clear technical communication across international teams, he pairs strong statistical intuition with hands-on systems and database experience to turn noisy, high-dimensional measurements into actionable models.
11 years of coding experience
1 year of employment as a software developer
Bachelor of Science (B.S.), Physics and Mathematics, 3.82/4.00, Bachelor of Science (B.S.), Physics and Mathematics, 3.82/4.00 at Duke University
Master's Degree, Physics, Master's Degree, Physics at Yale University
University of Illinois Urbana-Champaign
Latin