Geospatial Data Scientist

Role overview

Collect, process, and analyze geospatial data to produce useful findings and data products. The work spans satellite imagery, spatial modeling, machine learning, and cloud-based workflows, with collaboration across teams to develop and deliver geospatial solutions. This is a six-month contract for candidates based in the United States who are authorized to work there.

Responsibilities

- Process satellite imagery from sources such as Sentinel, Landsat, Planet, MODIS, and VIIRS. - Develop spatial models for applications including vegetation, land cover, wildfire, drought, water stress, and soil moisture. - Build machine learning workflows for tasks such as classification, segmentation, and prediction. - Create scalable pipelines using Python, Google Earth Engine, and cloud services; combine imagery with sources such as LiDAR, radar, climate, and sensor data. - Produce reusable scripts, notebooks, dashboards, maps, reports, and other data products. - Contribute to research, prototypes, and solution development, and explain findings to collaborators or clients.

Requirements

- Bachelor’s or master’s degree in GIS, remote sensing, geospatial or environmental science, computer science, or a related field. - Strong Python skills and experience with geospatial data analysis. - Understanding of machine learning concepts and applied modeling. - Ability to work independently and communicate technical results clearly. - Authorization to work in the United States.

Nice to have

- Familiarity with tools such as NumPy, Pandas, SciPy, scikit-learn, PyTorch, or TensorFlow, and geospatial libraries such as GDAL, Rasterio, GeoPandas, Xarray, or rioxarray. - Experience with remote sensing preprocessing, spectral indices, cloud platforms, SAR, environmental time series, or land-cover mapping. - Dashboard or web mapping experience, or work with agricultural, climate, or environmental data.

Benefits and work setup

Six-month, remote contract; candidates must be based in the United States.