Overstory is tackling the climate crisis by harnessing cutting-edge technology to enhance electrical grid resilience. As a Staff Machine Learning Engineer, you will lead the development of the Wildfire Fuel Detection Model, working closely with teams to ensure its accuracy and robustness while mentoring other engineers.
Responsibilities:
- Architect and build advanced ML models to map and predict vegetation and fuel conditions across diverse geographies
- Design and maintain robust data and feature pipelines for large-scale geospatial and temporal data
- Partner with wildfire science and product teams to define modeling objectives and evaluation metrics tied to real-world impact
- Build reproducible experimentation frameworks and model evaluation workflows
- Scale models from research to production with a focus on performance, reliability, and explainability
- Lead the evolution of ML systems, tooling, and processes — ensuring that our wildfire fuelscape models remain state-of-the-art and maintainable
- Collaborate with MLOps peers to streamline training, inference, and monitoring in production environments
Requirements:
- 10+ years of experience designing and building production-grade ML pipelines and systems – but don't filter yourself out if you feel you're a strong candidate with 6+ years
- Strong background in deep learning, computer vision, or remote sensing
- Skilled in designing end-to-end ML systems — from data ingestion and preprocessing to deployment and monitoring
- Hands-on experience with frameworks like PyTorch, TensorFlow, XGBoost, or LightGBM, and data tools like Dask, Spark, or GeoPandas
- Familiarity with GCP and Vertex AI, or similar cloud-based ML platforms
- Strong communication skills and ability to collaborate across technical and scientific domains
- Comfortable leading architectural discussions and mentoring other engineers
- You are based in the US or Canada
- Background in wildfire science, forestry, or remote sensing
- Experience integrating physics-based models with ML or working with active learning and uncertainty quantification
- Experience in model interpretability and data provenance for environmental ML systems
- Experience with deep learning models for weather or climate data
- Experience in remote-first or globally distributed teams