I am an Associate Professor at New York University, Director of the Center for Health Data Science, and Director of the AI and Emerging Technologies Master's Program. My research develops computational methods to evaluate, deploy, and govern AI systems in real-world environments, particularly in healthcare, public health, and public-sector settings. My group works at the intersection of artificial intelligence, health, climate, and society. We study how AI systems behave across populations, institutions, and deployment contexts, with a particular focus on robustness, fairness, reasoning, and decision-making under real-world constraints. Our work combines methodological advances in machine learning with collaborations involving healthcare systems, governments, community organizations, and international partners. Current areas of focus include: Robustness, fairness, and generalization of machine learning systems across populations and institutions (e.g., ACM FAccT 2021; ICML 2023; CLeaR 2025). Evaluation and deployment of generative AI and large language models in healthcare and public-sector settings (e.g., npj Digital Medicine 2024; ICML 2026; ACL 2026). AI reasoning, clinical decision support, and human-AI collaboration. Environmental, climate, and urban-health applications using satellite imagery, street-view imagery, wearable sensors, and large-scale observational data (e.g., ACM Journal on Computing and Sustainable Societies 2025; CVPR Workshop 2022). Data science methods for understanding social determinants of health, health equity, and population health (e.g., Lancet Digital Health 2024; PNAS 2024). A central theme across this work is moving beyond benchmark performance to understand how AI systems function under the heterogeneity, uncertainty, and operational constraints that characterize real-world environments. Ultimately, I study, design and show how AI can be designed, evaluated, and deployed to improve decision-making for individuals, organizations, and communities.