Senior Geospatial Machine Learning Engineer

About the Role

Join a fast-growing, mission-driven climate tech company using AI and advanced satellite imagery to help electric utilities manage vegetation risks — preventing wildfires, reducing outages, and building a more resilient energy grid. You'll be part of a multidisciplinary Vegetation Modeling team working at the intersection of geospatial data, machine learning, and real-world environmental impact.

As a Senior Geospatial Machine Learning Engineer, you'll spend most of your time working within small, focused groups to experiment with, build, and improve algorithms that help understand how vegetation affects utility infrastructure. Past work has included co-registering imagery, locating critical energy infrastructure, and identifying tree species, heights, and health. Current work spans maintaining and improving these solutions as well as developing new features to assess wildfire risk and evaluate vegetation management strategies.

What You'll Do

• Develop new vegetation intelligence products using standard geospatial Python libraries alongside machine learning and deep learning tools.

• Support existing products through data exploration, model improvements, and bug fixes — working regularly with QGIS, Dagster, Sentry, and Grafana.

• Lead projects and initiatives end-to-end: own planning, execution, and delivery, ensuring the value of contributions is clearly communicated to stakeholders across the organisation.

• Build tooling and processes to measure the performance and business value of your team's work, supporting data-driven prioritisation decisions.

• Collaborate closely with upstream data ingestion teams and downstream delivery/refinement teams throughout the full scientific product lifecycle.

• Contribute to shaping team culture, processes, and technical direction at an early-stage, high-growth company.

What We're Looking For

Required

• 8–10+ years of relevant experience in machine learning engineering, geospatial engineering, or a closely related field.

• Strong proficiency in Python, with hands-on experience using geospatial libraries: GDAL, Rasterio, Shapely, Fiona, GeoPandas.

• Experience with scientific Python tools: NumPy, SciPy, scikit-learn, Pandas.

• Practical experience with deep learning frameworks: PyTorch and/or Tens