Machine Learning Engineer

GreenAnt is a startup at the intersection of geospatial intelligence and AI-driven climate risk analysis. We leverage cutting-edge satellite data, machine learning models, and domain expertise to provide actionable insights for climate adaptation, disaster risk management, and environmental monitoring. Our flagship platform, Desidera, integrates satellite analytics with AI forecasting tools to support the insurance, agriculture, and sustainability sectors.

We are seeking a highly skilled Machine Learning Engineer with a solid foundation in geospatial analysis to spearhead the development of advanced forecasting models for climate risk and environmental resilience. The ideal candidate will possess deep expertise in both ML-driven predictive modeling and GIS data processing, enabling them to tackle complex, climate-related geospatial challenges.

• Develop and maintain distributed data processing pipelines for high-resolution environmental and geospatial datasets.
• Build and refine machine learning models for a variety of geospatial forecasting tasks, including climate risk assessment, flood modeling, and land-use change prediction.
• Leverage Graph Neural Networks (GNNs) and other spatio-temporal AI frameworks to identify and analyze patterns in environmental and hydrological data.
• Implement scalable systems for real-time ingestion and processing of remote sensing data (e.g., Sentinel-1 SAR, Landsat, MODIS).
• Integrate physically-based environmental models (e.g., LISFLOOD, HEC-RAS) with AI models to enhance predictive accuracy in climate and hydrological simulations.
• Optimize high-performance computing (HPC) resources for large-scale environmental modeling and AI inference.
• Collaborate with climate scientists, AI researchers, and software engineers to incorporate ML models into GreenAnt’s Desidera platform.

• MSc or PhD in Geoinformatics, Environmental Engineering, Remote Sensing, Computer Science, or a related field.
• Expertise in GIS software & programming: ArcGIS, QGIS, GDAL, PostGIS, and Python geospatial libraries (Geopandas, Rasterio, Fiona, Pyproj).
• Deep understanding of Machine Learning techniques: CNNs, RNNs, GNNs, and transformers, specifically for spatio-temporal data analysis.
• Experience with hydrological/environmental modeling: LISFLOOD, HEC-RAS, CaMa-Flood, SWAT.
• Cloud computing experience: AWS/GCP/Azure for large-scale geospatial data processing (e.g., AWS Lambda, GEE, S3, EC2, Kubernetes, Docker).
• Proficiency in high-performance computing (HPC) for large-scale environmental simulations.
• Excellent problem-solving skills and the ability to work independently on complex geospatial challenges.

• Work on groundbreaking climate risk solutions with immediate real-world impact.
• A dynamic, international, and highly innovative team environment.
• Competitive salary and equity options.
• Flexible remote work policy.
• Access to top-tier computing infrastructure and collaborative research opportunities.

Join us and play a pivotal role in shaping the future of geospatial AI for climate resilience. If you’re passionate about machine learning, environmental innovation, and cutting-edge technology, we’d love to hear from you!