Vision ML Postdoc: Satellite Imagery & PV Systems

National Laboratory of the Rockies

Golden (CO)

On-site

USD 77,000 - 126,000

Full time

14 days+

Get a reply from this employer

Your resume and cover letter, tailored to exactly what they’re hiring for.

Get past ATS filters

Benefits offered by this job

Medical insurance

Dental insurance

Vision insurance

Short-term disability

Pension benefits

403(b) with employer match

Life and AD&D insurance

Paid time off

Relocation assistance

Job summary

National Laboratory of the Rockies in Golden, CO, seeks a postdoctoral researcher to advance machine-learning and computer-vision methods for PV systems, using satellite imagery and large-scale datasets. You will develop algorithms for image-based change detection and integrate results with PV performance data to support fleet-level analyses.

The role requires a recent PhD, experience with PyTorch/TensorFlow/OpenCV, and a strong background in geospatial data.

Qualifications

Must be a recent PhD graduate within the last three years.
Must meet educational requirements prior to employment start date.
Demonstrated experience with computer vision and/or machine learning, particularly image segmentation, object detection, feature extraction, image registration, or change detection.
Experience working with satellite, aerial, remote-sensing, or geospatial imagery.
Experience developing or adapting algorithms for analysis of large image datasets.
Experience with parallel computing, high-performance computing, distributed computing, and/or cloud-based computational workflows.
Experience with large-scale time-series or operational datasets.
Experience integrating heterogeneous datasets, such as imagery, geospatial information, operational measurements, and system metadata.
Experience quantitatively validating computational methods, including assessment of algorithm accuracy, uncertainty, and limitations.
Experience with PyTorch, TensorFlow, OpenCV, scikit-learn, GDAL, Rasterio, GeoPandas, xarray, or similar tools.
Experience with photovoltaic systems, renewable-energy performance data, or related energy-system applications.
Experience developing open-source scientific software, reusable computational tools, or public research datasets.

Responsibilities

Developing, adapting, and validating computer-vision and machine-learning methods for analyzing PV systems from satellite and aerial imagery.
Developing methods for detecting and characterizing changes in PV systems across imagery collected at different points in time.
Processing and analyzing large geospatial, image, and PV operational datasets.
Integrating image-derived information with PV performance, system metadata, permitting, and other complementary datasets.
Developing scalable computational workflows for application across large numbers of PV systems and images.
Evaluating algorithm accuracy, uncertainty, limitations, and generalizability using known-change and no-change systems.
Developing reproducible research software and data-analysis workflows using version control and collaborative software-development practices.
Applying statistical and machine-learning approaches to identify changes, anomalies, and trends in PV system performance.
Publishing research results in peer-reviewed journals and presenting findings at technical conferences and project meetings.
Collaborating with researchers across disciplines including PV performance and reliability, geospatial analysis, machine learning, materials, recycling, circularity and energy systems analysis.