Summary
Bruno Barbarioli is a research scientist based in Chicago who builds AI agents and tooling to automate replication and robustness checks for social science research, with a focus on Economics and Political Science. He holds a PhD in Computer Science from the University of Chicago and brings a decade of experience spanning machine learning, statistics, and systems engineering applied to reproducibility, compression, and scalable data infrastructure. At the Institute for Replication he designs LangChain-based agents that execute multi-language code, fine-tunes open-source LLMs with PEFT for error analysis, and created a typed contract protocol for autonomous agent negotiation and reputation. His background includes practical data science roles in industry and academic projects that produced novel compression and subsampling methods for geospatial and time series data, signaling a strong blend of theoretical rigor and production-minded implementation. Dual citizenship (US/Italy) and recent collaboration with the World Bank’s DIME reflect his ability to operate at the intersection of research, policy, and large-scale deployment.
10 years of coding experience
8 years of employment as a software developer
Doctor of Philosophy - PhD, Computer Science, Doctor of Philosophy - PhD, Computer Science at University of Chicago
Master of Science (M.S.), Statistics, Master of Science (M.S.), Statistics at Universidade Federal de Minas Gerais
English, Portuguese, Italian