Zehao Xu
Senior Data Scientist
Markham, Ontario, Canada
Summary
🤩
Rockstar🎓
Top SchoolZehao Xu is a Senior Data Scientist with a PhD in Statistics from the University of Waterloo and eight years of experience building production-ready ML systems and measurement frameworks. Based in Markham, Ontario, he has driven scalable prevalence estimation and GenAI safety measurement at Pinterest, replacing costly bespoke pipelines with reusable, pivot-capable solutions. His background spans fraud detection and biometric analysis at fintech Sardine—where he cut name-matching false positives from 25% to 3%—and visualization-focused R development at Plotly. Zehao blends rigorous research with hands-on engineering, contributing full-stack work to open-source Dash apps for interactive 3D molecular visualization. He’s comfortable moving models into production, instrumenting monitoring, and improving UX alongside backend logic. His combination of academic depth and applied product impact makes him adept at turning complex statistical research into operational, cost-saving tools.
7 years of coding experience
4 years of employment as a software developer
Bachelor of Science - BS, Statistics, Bachelor of Science - BS, Statistics at Southwestern University of Finance and EconomicsDoctor of Philosophy - PhD, Statistics, Doctor of Philosophy - PhD, Statistics at University of Waterloo
Stackoverflow
69reputation
5kreached
2answers
8questions
Github Skills (15)
plotly-dash10
dashjs10
plotly10
r10
bioinformatics9
css7
rcpp6
gridextra6
shiny6
tcl-tk6
ggplot6
tcl6
graphic6
grid6
javascript5
Programming languages (6)
Github contributions (5)
plotly/dash-sample-apps
Jul 2019 - Jul 2019
Open-source demos hosted on Dash Gallery
Role in this project:
Full-stack Developer
Full-stack DeveloperContributions:13 commits, 14 PRs, 35 pushes in 17 days
Contributions summary:Zehao contributed to the development of a Dash application for visualizing and interacting with molecule 3D data. Their commits show changes to the application's core logic (`app.R` file), including functions for reading and processing PDB data. The user also modified CSS files to improve the application's user interface and resolved a bug related to file uploading, indicating a focus on both backend functionality and frontend presentation.
dashhostedplotly-dashplotlydata-visualization
z267xu/loon
Jul 2019 - Jun 2020
A Toolkit for Interactive Statistical Data Visualization
Contributions:73 pushes in 10 months
data-analysisdata-sciencestatisticaldata-visualizationtableau
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.