Profile cover
I

Senior ML Engineer — Climate Forecasting

Isabelle Fontaine

Full-time · Senior · Berlin

About the role

The models that currently inform climate adaptation planning were not designed for the resolution or the update frequency that local governments, infrastructure operators, and agricultural planners actually need to make decisions. We are building them. Our team of twelve combines climate scientists, remote sensing specialists, and ML engineers working on downscaled climate projections, extreme event detection, and seasonal forecasting for regions where the gap between coarse global models and local decision-making is most consequential. This is not a job for someone who wants to work on climate as a side narrative to an otherwise conventional ML role. The physics matters. The data quality issues are domain-specific. The evaluation methodology for climate models is different from standard ML evaluation and you will need to engage with it seriously. We work in Python on GCP, with heavy use of Airflow for data pipeline orchestration and PyTorch for model development. Our data is predominantly geospatial and multitemporal. If you have a background in atmospheric science, Earth observation, or scientific computing alongside your ML experience, we will find the conversation immediately interesting.

Responsibilities

  • Design and train spatiotemporal ML models for regional climate variable downscaling and extreme event detection
  • Build and maintain data pipelines ingesting ERA5, CMIP6, satellite observations, and in-situ sensor networks
  • Develop evaluation frameworks appropriate to probabilistic climate prediction tasks
  • Collaborate with climate scientists to translate domain constraints into model design and training decisions
  • Document model architecture decisions, training data provenance, and evaluation methodology in a form suitable for scientific review

Requirements

  • 5+ years of ML engineering with production model deployment experience
  • PyTorch for geospatial or scientific data modelling — experience with irregular grids, missing data, and spatiotemporal sequences is a strong advantage
  • GCP at operational depth: Vertex AI, Cloud Storage, BigQuery, and Dataflow — not just familiarity
  • Airflow for orchestrating multi-step scientific data pipelines across large geospatial datasets
  • Docker for reproducible scientific computing environments and model serving
  • Strong Python: readable, tested scientific code that a climate scientist can review and a software engineer can maintain
  • Background in atmospheric science, Earth observation, or a related physical science discipline is valued above most additional ML credentials

Benefits

  • Work on a problem with direct consequences for climate adaptation in underserved regions
  • Full remote — our team is distributed across Europe, East Africa, and North America
  • $115,000 – $140,000 base salary
  • $2,000 annual conference and research budget
  • Access to significant GCP compute credits through our research partnerships

Job Type

Full-time

Level

Senior

Language

English

Salary Range

$115,000 – $140,000

AI Expertise

AI & Machine Learning Engineers

Ready to apply for this role?

Create a free talent account in under 2 minutes.

  • Apply to verified AI companies
  • Get AI-matched job recommendations
  • Message hiring managers directly
  • Build your public AI talent profile
Create free account & apply Log in