Postdoctoral Associate — Geospatial and Environmental Machine Learning (GEM) Lab

Lead and implement GeoAI research including geospatial Implicit Neural Representations (GeoINRs) and scaling laws for spatiotemporal pretraining data decisions, integrating implicit neural representations and physical models. Collaborate on and lead team projects, including mentoring PhD students; no teaching expectation. Work supports hybrid neural fields, feature detection (buildings, agricultural fields, wind turbines), and community benchmarks, with collaborators across Microsoft AI for Good and partner universities. Requirements: PhD in Computer Science or closely related field (completed or expected by start); first-author publications at top CV/ML venues; strong Python and PyTorch; mathematical maturity in linear algebra, probability, and optimization. Preferred: neural-field/implicit representations, geospatial/remote-sensing ML, large-scale training, uncertainty quantification, scaling laws, open-source releases. Apply with CV, cover letter, 1-page research statement, and three references. Apply by October 30, 2026 for full consideration; posting closes November 13, 2026. Visa sponsorship is not available.