Santiago E. Cortés-Gómez

I am a Machine Learning PhD candidate at Carnegie Mellon’s School of Computer Science, advised by Professor Bryan Wilder. My research focuses on developing the principled scaffolding that AI systems need to be deployed responsibly at the policy level, particularly in public and clinical health domains. I’m most excited by projects that connect machine learning theory with real-world decision-making, I’m drawn to work that combines principled design (Whether that means a formal argument or a rigorous engineering procedure) with practical implementation to ensure AI systems remain reliable under uncertainty. These days I am quite interested about higher level explanations for AI interpretability, among them, how to model beliefs or the behaviour of a group of agents. In particular, I am interested in finding results that are also consistent with interpretability results at the design level, for example, those drawn from Mechanistic interpretability. My CV can be found here.