Summary
Irina Cristali is a data scientist and machine learning engineer with a decade of experience building predictive models and scalable analytics, currently applying her skills at Massive Dynamics in Princeton. She holds a PhD in Statistics from the University of Chicago, where her dissertation produced novel methods in causal inference, network analysis, and representation learning—work that reduced missingness in a 2.7M-person family network by 91.6% and established a probabilistic lens on CLIP representations. Her research blends rigorous theory with production-minded implementation (TensorFlow) and has outperformed standard baselines on large real-world networks. Irina has also translated her expertise into industry settings through a Biogen biostatistics internship focused on causal mediation for time-varying outcomes and survival models. She mentors and teaches data science across levels, from high-school students to graduate researchers, and brings an uncommon combination of probabilistic theory, causal methods, and practical systems experience.
10 years of coding experience
4 years of employment as a software developer
Bachelor of Science - BS Mathematics and Statistical Science (Double Major), Bachelor of Science - BS Mathematics and Statistical Science (Double Major) at Duke University
Ph.D. Statistics, Ph.D. Statistics at University of Chicago
English, Romanian, French