Microsoft's AI for Earth is looking for a Senior Geospatial Data Engineer, who will play a role in accelerating the impact of this program via a “Planetary Computer”: a set of geospatial data and distributed computing tools that enable global-scale analyses for conservation and sustainability.
In this role, you will lead the design and implementation of architectures for geospatial data ingestion and release through the Planetary Computer infrastructure, as well as via Azure Open Datasets. Applicants should have at least three years of software development experience, and be fluent with Python, geospatial raster analysis tools, and GIS software.
Senior Geospatial Data Engineer, AI for Earth - Sustainability
Microsoft’s AI for Earth program accelerates innovation at the intersection of machine learning and environmental science, through grants, data hosting, and technology development. We build machine learning and cloud computing tools that advance the state of the art in conservation technology, and we work directly with grantees, customers, and partners to apply those tools to real-world problems. The next milestone for the AI for Earth program is to accelerate the impact of this work via a “Planetary Computer”: a set of geospatial data and distributed computing tools that enable global-scale analyses for conservation and sustainability.
This role will lead the design and implementation of architectures for geospatial data ingestion and release through our Planetary Computer infrastructure, as well as via Azure Open Datasets. The core of the work will focus on building maintainable, high-bandwidth data retrieval and transformation pipelines to prepare geospatial data sets for use on the cloud.
- Design and implement data processing and ingestion pipelines
- Work with external data providers to manage data preparation, ingestion, and documentation
- Prepare documentation and examples for geospatial data processing tasks that depend on these data sets
- Work with external collaborators to ensure that data and documentation are user-friendly
- Work with our data science team to facilitate the development of machine learning tools and applications on top of our geospatial data archives
- Fluency with Python required
- Fluency with geospatial raster analysis tools (e.g. rasterio, GDAL) required
- Fluency with GIS software (e.g. ArcGIS, QGIS, CARTO, Mapbox) required
- Fluency with Linux required
- Fluency with cloud (Azure, AWS, or GCP) infrastructure required
- Fluency with collaborative platforms (e.g. GitHub, GitLab) required
- Bachelors or higher in in computer science, software engineering, remote sensing, geography/GIS, or related fields required
- At least three years of software development experience required
- Fluency with open-source, cloud-based geospatial analysis tools (e.g. Pangeo, STAC) preferred, but not required
- Fluency with distributed computing/querying frameworks (e.g. Kubernetes, Hadoop, Spark, Dask, Azure Batch, BigQuery) preferred, but not required
- Experience with Jupyter preferred, but not required
- Familiarity with machine learning preferred, but not required
- Familiarity with R preferred, but not required
- Interest and comfort in engaging with the environmental science and sustainability communities preferred, but not required
The team is in Redmond, Washington; candidates able to relocate to the Puget Sound area are preferred, but remote candidates will be considered.
Visit Microsoft's career opportunities page here to view full job details and to begin your application.
Meet others in our community working with GIS professionally by visiting our forum!