Postdoctoral Research Position in AI for Healthy Climate Adaptation

Overview

Position Description
The National Studies on Air Pollution and Health (NSAPH) group, led by Prof. Francesca Dominici, invites applications for a full-time Postdoctoral Research Fellow to join a massive research effort developing next-generation AI methods for healthy climate adaptation. The position will focus on building and evaluating foundation models for large-scale spatiotemporal health and environmental data. Our team leverages nationwide Medicare claims data for older adults in the United States, linked with rich contextual information, including census, weather, and air pollution data. The overarching goal is to develop domain-specific foundation models that support tasks such as forecasting, interpolation/extrapolation, downscaling, and “what-if” scenario analysis relevant to climate-related health risks and adaptation strategies.

Duties and Responsibilities
-Design, implement, and evaluate deep learning models for spatiotemporal data, with an emphasis on medium-scale foundation models.
-Leverage model embeddings in causal inference pipelines for health effects and adaptation policy evaluation.
-Work with large, high-dimensional datasets (Medicare claims, census, weather, pollution, and related data), including data preprocessing, integration, and harmonization.
-Lead and contribute to manuscripts for high-impact journals and conferences (e.g., Nature-like journals or top CS conferences).
-Present findings in internal meetings and at national/international conferences.
-Collaborate with an interdisciplinary team of biostatisticians, computer scientists, and climate scientists.
-Contribute to open-source code, reproducible research workflows, and, where possible, public tools or model artifacts.

Basic Qualifications

PhD (completed or near completion) in one of the following or a closely related field:

-Computer Science
-Statistics / Biostatistics
-Applied Mathematics
-Data Science

Demonstrated expertise in modern machine learning, including at least one of the following:Deep learning (e.g., transformers, sequence models, representation learning)
-Spatiotemporal modeling or geospatial/temporal data analysis
-Medium-to-Large-scale foundation models pretraining/fine-tuning paradigms
-Strong programming skills in Python and experience with PyTorch, required to have experience developing code with a team through collaborative version control

Experience working with large datasets and cloud computing environments.
Solid background in statistical modeling and inference
Excellent written and oral communication skills, with a track record of peer-reviewed publications commensurate with career stage.

Additional Qualifications

Prior experience with one or more of:
Health claims data, EHRs, or other large-scale health/administrative datasets
Environmental, climate, or air pollution exposure data
Causal inference methods
Uncertainty quantification and model calibration for decision-making
Familiarity with interdisciplinary work at the interface of climate, environment, and health.