Rice University
Just Landed
New Today
Postdoctoral Associate in Multimodal & Graph AI for Earth Systems at Rice University Rice University in United States
Degree Level
Postdoc
Field of study
Computer Science
Funding
Funded by a grant and soft and/or restricted funds. Initial one-year term, renewable for up to two to three years subject to performance and funding availability. Competitive salary and full Rice University benefits package are offered.
Deadline
Dec 2, 2026
Country
United States
University
Rice University
How do I apply for this?
Sign in for free to reveal details, requirements, and source links.
Apply for this position
Keywords
Suggested positions
About this position
Postdoctoral Research Associate – Multimodal & Graph AI for Earth Systems at Rice University (Houston, Texas, United States).
The MUSE (Multimodal AI for Earth System Discovery) research cluster is seeking a postdoctoral researcher to develop multi-domain graph neural networks (GNNs) and foundation models for Earth system modeling, state estimation, and forecasting. The project spans irregular, multi-scale Earth observations such as river networks, seismic stations, InSAR satellite data, distributed acoustic sensing, and subglacial sensors.
Research themes include hydrology, flood dynamics, cryosphere, aquifer mechanics, and earthquake processes, with an emphasis on reusable, scale-adaptive, graph-based architectures, physics-informed learning, and uncertainty quantification. The role also involves proposal development and collaboration across ML, remote sensing, geophysics, Computer Science, Electrical & Computer Engineering, and Earth, Environmental and Planetary Sciences.
Eligibility: Ph.D. in Computer Science, Data Science, Geophysics/Earth Sciences, Applied Mathematics, Electrical Engineering, Environmental Engineering, or a related quantitative field. Strong Python and deep learning skills are required, especially with PyTorch, PyTorch Geometric, or DGL. Experience with spatial-temporal data, PINNs, neural operators, surrogate modeling, UQ, and HPC/cloud distributed training is preferred.
Funding: The position is grant-funded, with an initial one-year appointment renewable up to two to three years depending on performance and funding. Rice states that the role includes competitive salary and full benefits.
How to apply: Submit a single PDF through the Rice University Application Portal containing a cover letter, CV, research statement, and three professional references. Review begins on December 1, 2026, and applications are accepted until the position is filled; the posted apply-before date is 2026-12-02.
Funding details
Funded by a grant and soft and/or restricted funds. Initial one-year term, renewable for up to two to three years subject to performance and funding availability. Competitive salary and full Rice University benefits package are offered.
What's required
Ph.D. in Computer Science, Data Science, Geophysics/Earth Sciences, Applied Mathematics, Electrical Engineering, Environmental Engineering, or a related quantitative field. Strong background in deep learning on graphs, geometric deep learning, or large-scale foundation model architectures with interest in physical or geoscientific systems. High proficiency in Python and deep learning frameworks such as PyTorch, PyTorch Geometric, or DGL. Demonstrated track record of peer-reviewed publications in high-impact computational or geoscience journals and conferences. Preferred: experience with spatial-temporal or irregularly sampled physical data, PINNs, neural operators, neural surrogate modeling, uncertainty quantification, hybrid ML with physical priors, and HPC/cloud distributed training.
How to apply
Submit all required materials through the Rice University Application Portal as a single PDF uploaded under “CV/Resume.” Include a cover letter, CV, research statement, and contact information for three professional references. Informal inquiries may be sent to Rice EEPS at [email protected].
More information can be found here
Ask ApplyKite AI
How do I apply for this?
Sign in for free to reveal details, requirements, and source links.