Staff Machine Learning Engineer (Wildfire)

Location: Remote, with candidates required to live and work in the United States, Canada, the Netherlands, the United Kingdom, Ireland, Estonia, Portugal, France, Sweden, Switzerland, or Denmark. Working hours must align with Eastern North America time zones: NST, AST, or EST.

Company

hirify.global develops AI and satellite-imagery solutions that help electric utilities identify vegetation risks, prevent outages, reduce wildfire risk, and build a more resilient grid.

What you will do

• Lead the development and scaling of the Wildfire Fuel Detection Model for mapping vegetation structure, fuel loads, and wildfire risk.
• Architect advanced machine learning models using large-scale geospatial, temporal, satellite, and environmental data.
• Design and maintain data and feature pipelines, experimentation frameworks, and model evaluation workflows.
• Partner with data scientists, ML engineers, wildfire science specialists, and product teams to define objectives and impact-focused evaluation metrics.
• Scale models from research to production with emphasis on performance, reliability, explainability, and maintainability.
• Lead ML systems and tooling decisions, collaborate with MLOps engineers, and mentor other engineers.

Requirements

• 10+ years of experience designing and building production-grade machine learning pipelines and systems.
• Experience working at the intersection of machine learning, geospatial data, and environmental science.
• Background in wildfire science, forestry, or remote sensing.
• Strong experience with deep learning, computer vision, or remote sensing, and end-to-end ML systems from ingestion and preprocessing through deployment and monitoring.
• Hands-on experience with PyTorch, TensorFlow, XGBoost, or LightGBM, plus Dask, Spark, or GeoPandas.
• Familiarity with GCP, Vertex AI, or similar cloud-based ML platforms, along with architectural leadership, mentoring, and cross-domain communication skills.

Nice to have

• Experience integrating physics-based models with machine learning, or working with active learning and uncertainty quantification.
• Experience with model interpretability and data provenance for environmental ML systems.
• Experience building deep learning models for weather or climate data.
• Experience working in remote-first or globally distributed teams.

Culture & Benefits

• Flexible, autonomous, and collaborative remote working environment.
• Home office stipend, coworking budget, and ongoing education budget.
• Competitive compensation and benefits tailored to the candidate’s location.
• Annual in-person team gathering and opportunities for occasional in-person collaboration.
• Mission-driven work focused on reducing wildfires, protecting natural resources, and addressing the climate crisis.