Scientific Software Engineer (AI-based Weather Forecasting)
Immigration Policy Lab
Scientific Software Engineer (AI-based Weather Forecasting)
80%-100%, Zurich, fixed-term
In recent years, AI-based weather forecasting models have demonstrated impressive speed and skill. However, most existing systems operate at relatively coarse spatial resolutions, limiting their usefulness in regions with complex terrain. Switzerland’s topography and the demand for precise, frequently updated forecasts require models that operate at very high resolution and integrate seamlessly into operational forecasting workflows.
Project background
In collaboration with Center for Climate Systems Modeling (C2SM) at ETH Zurich and various European weather centers, MeteoSwiss is leading an initiative to develop and deploy a next-generation, high-resolution AI-based weather forecasting system.
The project aims to build a forecasting system capable of producing predictions across multiple temporal scales, from short-range to up to 10 days ahead, using recent advances in deep learning. A central component of this effort is Anemoi, a framework developed by the European Centre for Medium-Range Weather Forecasts (ECMWF) to support AI applications in weather and climate science.
Job description
- Join the post-processing and verification team at MeteoSwiss as a Scientific Programmer / Software Developer
- Contribute to the implementation of a state-of-the-art, ML-based forecasting system
- Focus on data processing pipelines, post-processing, and verification workflows
- Collaborate closely with scientists, ML researchers, and operational teams
- Ensure forecast outputs meet the needs of diverse users
- Support reliable integration of forecast products into production environments
- Design and implement new forecasting products
- Develop scalable, maintainable processing pipelines
- Contribute to the evolution and long-term sustainability of the system
- Tackle complex problems and collaborate across disciplines
- Contribute across multiple stages of the workflow as the system matures
The position is limited to two years.
Profile
We welcome applications from candidates with diverse backgrounds who meet most (not necessarily all) of the following criteria:
- MSc or PhD in natural sciences (e.g. physics, meteorology), data science, computer science or a related field
- Experience in scientific software development
- Solid understanding of numerical weather prediction and meteorological applications
- Experience with, or strong interest in, machine learning, ranging from classical methods (e.g. random forests) to modern deep learning approaches (e.g. graph neural networks, transformers)
- Strong Python skills; experience with Xarray and Earthkit is an advantage
- Experience with parallel or distributed computing is a plus
- Familiarity with large-scale or production-level software systems
- Interest in DevOps practices and sustainable software engineering
- Willingness to contribute across the full workflow, from development to maintenance and operations
- A collaborative mindset, with the ability to take ownership of tasks and communicate effectively within a team
- Motivation to work in a diverse, interdisciplinary, and international environment
Workplace
Workplace
We offer
- A unique opportunity to help shape the next generation of AI-based weather forecasting
- Direct involvement in bringing cutting-edge ML research into operational use
- Work on production-grade systems at the scale of a national meteorological service
- A position at the interface of research and operations, bridging academic innovation and real-world forecasting
- Collaboration with international research groups and European weather centers
- Use of modern scientific and ML software stacks, including Python, PyTorch, Xarray, and container technologies
- A supportive, motivated, and interdisciplinary team within a mission-driven public service organization
- The opportunity to combine scientific impact, societal relevance, and modern software engineering
We value diversity and sustainability
Curious? So are we.
We look forward to receiving your online application with the following documents:
- Motivation letter
- CV
- Reference letters
Further information can be found at the C2SM and MeteoSwiss websites. Questions regarding the position should be directed to Daniele Nerini; daniele.nerini@meteoswiss.ch (no applications).
Please note that we exclusively accept applications submitted through our online application portal. Applications via email or postal services will not be considered.
We would like to point out that the pre-selection is carried out by the responsible recruiters and not by artificial intelligence.
For recruitment services the GTC of ETH Zurich apply.