Summary
Julia Kang is a data scientist with a decade of experience applying ML and analytics to trust & safety, payments, ads monetization, and growth at top tech firms including Snap, Twitter, Facebook, and Venmo. She blends rigorous Cornell-trained quantitative foundations in operations research and CS with hands-on applied ML skills from Google's intensive fellowship, delivering product-focused models in high-risk, high-scale domains. Her recent work centers on Trust & Safety at Snap, building systems that balance user protection and platform integrity while previously driving marketing and SMB ad optimization. Comfortable across Python, TensorFlow, SQL, and cloud tooling, she has moved between product analytics and production ML roles, making her adept at translating metrics into reliable model-backed decisions. Colleagues describe her as pragmatic and detail-oriented—able to navigate ambiguous problems where safety, fraud, and monetization intersect. Reachable at jk2534@cornell.edu, she pairs technical depth with domain experience that few data scientists acquire so broadly across payments, ads, and trust.
10 years of coding experience
5 years of employment as a software developer
Bachelor of Science (B.S.), Operations Research and Information Engineering; Computer Science, Bachelor of Science (B.S.), Operations Research and Information Engineering; Computer Science at Cornell University
Radnor Senior High School
Chinese, English