Skip to main content
Bayi Glacier in Qilian Mountain, China (Credit: Xiaoming Wang, distributed via imaggeo.egu.eu)

Job advertisement Postdoctoral Associate in Machine Learning and Remote Sensing for Global Infrastructure Mapping

EGU logo

European Geosciences Union

www.egu.eu

Postdoctoral Associate in Machine Learning and Remote Sensing for Global Infrastructure Mapping

Position
Postdoctoral Associate in Machine Learning and Remote Sensing for Global Infrastructure Mapping

Employer

Cornell University


Location
Ithaca, United States of America

Sector
Academic

Relevant division
Hydrological Sciences (HS)

Type
Full time

Level
Entry level

Salary
The hiring rate of pay for the successful candidate will be determined considering a variety of criteria, including prior relevant work, qualifications, and unique applicable skills.

Required education
PhD

Application deadline
Open until the position is filled

Posted
4 November 2026

Job description

We invite applications for one Postdoctoral Associate position in machine learning and remote sensing for global-scale mapping of critical water infrastructure.

The candidate will join the DARE project (Dynamic Atlas of Riverine Ecosystems and Infrastructure), a large, interdisciplinary research initiative aimed at reconstructing the evolution of river systems and human infrastructure and assessing their impacts on freshwater ecosystems. The successful candidate will be part of a collaborative network of researchers and will have opportunities to engage with other projects within Schmidt Sciences’ Virtual Institute on Earth’s Water.

The successful candidate will develop scalable computational workflows to generate global infrastructure datasets and work closely with hydrologists to facilitate their integration into a large-scale hydrologic modeling framework. We are looking for a candidate with a PhD degree (or completion expected within 2–3 months) in Computer Science, Civil/Environmental Engineering, Remote Sensing, Geospatial Science, or a related field. The ideal candidate will have strong expertise in machine learning, particularly deep learning methods for processing and analyzing large-scale geospatial and remote sensing datasets (e.g., computer vision, convolutional neural networks, vision transformers). Experience with satellite imagery, geospatial data processing, and LLM-based workflows is desirable. Strong programming skills (e.g., Python) and demonstrated experience with high-performance computing, particularly GPU-based computing, are important qualifications. Familiarity with large-scale hydrology, water resources systems, or environmental modeling would be advantageous. The candidate should be well organized, proactive, and able to work both independently and as part of a team. Evidence of innovative scientific contributions during the PhD, strong communication skills, and proficiency in written and spoken English are important evaluation criteria.

The position will be based at Cornell University, under the supervision of Dr. Galelli, and will involve close collaboration with Dr. Kamal Chowdhury and Dr. Thomas Wild at the University of Maryland and Dr. Rafael Schmitt at the University of California, Santa Barbara. The candidate will take a leading role in preparing scientific publications, coordinate with researchers across the DARE consortium, and contribute to the broader research activities of the Critical Infrastructure Systems Lab, including occasional guidance to MSc and PhD students.

The successful candidate will be offered a Postdoctoral Associate position for 12 months, with the possibility of extension based on performance and availability of funds. The position is available immediately, with a preferred starting date in early 2027. Applications will be reviewed on a rolling basis until the position is filled.


How to apply

Applicants are required to submit a cover letter and a detailed curriculum vitae that includes a list of publications and the names and contact information for at least three references. The cover letter should ideally elaborate on specific research interests and how the candidate’s profile may fit within DARE. Application materials must be submitted at this address: dareproject.view@gmail.com