Geospatial Machine Learning Engineer

Join a fully remote, mission-driven climate technology environment where machine learning and satellite imagery are used to address critical infrastructure challenges.

• Develop and deploy new vegetation intelligence products using machine learning, deep learning, computer vision, geospatial Python libraries, and large-scale satellite or aerial imagery.
• Explore geospatial datasets, identify opportunities for model improvement, optimize existing ML solutions, and troubleshoot production issues.
• Maintain and enhance existing vegetation modeling products to improve accuracy, reliability, scalability, and overall impact.
• Lead technical projects end-to-end, from defining objectives and planning implementation through execution, delivery, and evaluation.
• Develop measurement frameworks, evaluation tooling, and performance metrics that enable data-driven decisions about model quality and impact.
• Monitor production models and investigate performance issues using appropriate observability, monitoring, and debugging tools.
• Work closely with upstream data ingestion teams to influence data pipelines, processing workflows, and platform architecture.
• Partner with downstream product and delivery teams to ensure geospatial ML outputs can be effectively integrated into customer-facing solutions.
• Use tools such as QGIS, Dagster, Sentry, Grafana, or equivalent platforms to analyze data, manage workflows, monitor systems, and diagnose issues.
• Communicate technical findings, project progress, model performance, and business impact clearly to technical and non-technical stakeholders.
• Contribute to engineering and ML best practices across a distributed team working across Europe and the Americas.
• Help translate complex environmental and geospatial problems into scalable machine learning solutions that support climate resilience and critical infrastructure.

• 5+ years of professional experience as a Machine Learning Engineer, Data Scientist, or in a closely related role, with demonstrated experience building and deploying production machine learning or deep learning models.
• Proven experience developing computer vision or deep learning models using satellite or aerial imagery.
• Strong proficiency in Python and geospatial Python libraries such as rasterio, geopandas, shapely, GDAL, or equivalent technologies.
• Solid understanding of geospatial data structures, formats, processing workflows, and analysis techniques.
• Professional experience with ML and deep learning frameworks such as PyTorch, TensorFlow, scikit-learn, or comparable tools.
• Experience designing, implementing, or maintaining data pipelines using orchestration and workflow tools such as Dagster, Airflow, dbt, or equivalent systems.
• Experience with QGIS or comparable geospatial visualization and analysis software.
• Strong understanding of model evaluation, performance measurement, monitoring, and debugging in production environments.
• Ability to work effectively with large-scale, complex datasets and translate technical findings into practical product or business decisions.
• Strong project ownership skills, with the ability to independently drive initiatives from planning through execution and delivery.
• Excellent communication and collaboration skills, particularly in distributed and cross-functional environments.
• Experience with multispectral or hyperspectral satellite imagery is a strong advantage.
• Background in vegetation analysis, forestry, agriculture, environmental monitoring, or related geospatial applications is highly valued.
• Familiarity with observability and monitoring tools such as Grafana, Sentry, Prometheus, or similar platforms is a plus.
• A genuine interest in climate technology, environmental applications, and using advanced technology to solve complex real-world problems is highly desirable.
• Candidates should be comfortable working in a fully remote environment and collaborating across multiple time zones.

• Fully remote working environment.
• Opportunity to work on technology with direct applications in climate action, wildfire prevention, and electrical grid resilience.
• Meaningful ownership of machine learning products and the opportunity to lead projects from concept through production.
• Collaboration with a geographically distributed team spanning Europe and the Americas.
• Exposure to advanced satellite imagery, geospatial data, computer vision, and large-scale machine learning systems.
• High-impact technical challenges involving real-world environmental and infrastructure problems.
• Competitive senior-level compensation package expected, commensurate with experience.
• Opportunity to contribute to the development of production ML systems rather than purely experimental or research-focused models.