Data Scientist / Data Scientistess

Swiss Data Science Center

This project arises from a collaboration between the Swiss Data Science Center (SDSC), MeteoSwiss, and EUMETNET.

The SDSC has been a National Research Infrastructure since 2025, evolving from a strategic focus area of the ETH domain, with EPFL and ETH Zurich as founding partners. Its mandate is to support academic groups and research, hospitals, industry, and the public sector at large, including cantonal and federal administrations. The center accompanies and supports their entire data science journey, from data collection and management to machine learning, AI, and industrialization. One of the key focuses of the SDSC is the areas of Climate, Weather, and Environmental Sciences, where we contribute significantly. The Center comprises a multi-disciplinary team of data and computer scientists and experts in various domains, with offices located in Zürich, Lausanne, and Villigen.

MeteoSwiss, the Federal Office for Meteorology and Climatology, leads and coordinates a larger effort on ML-based weather forecasting in collaboration with its European partners, which include other national weather services and ECMWF. In this role, MeteoSwiss provides domain science support, access to data and expertise, and assists in integrating ongoing efforts and existing codebases. It also defines requirements and provides feedback on project outcomes, overseeing the prototyping and operationalization of developments within the project.

The advertised position is funded by the EUMETNET (the European Meteorological Network) programme on Artificial Intelligence and Machine Learning for Weather, Climate, and Environmental Applications (E-AI). EUMETNET is a network of 33 European National Meteorological Services, existing to provide a framework for cooperative programmes among its members in fields of meteorology, data processing, and forecasting products.

Position Overview

We are seeking a data scientist with expertise in machine and deep learning to develop a seamless neural weather forecasting system. This collaboration involves the Swiss Data Science Center, MeteoSwiss, and EUMETNET, and is funded for a duration of two years.

The goal is to develop and implement a system capable of forecasting at various temporal scales of up to 10 days, utilizing recent advances in deep learning and machine learning. We expect the candidate to contribute to methodological advancements, develop, and enhance existing codebases, and participate in open-source initiatives in the domain, focusing on creating high-quality, reproducible, and robust code in Python. The candidate will utilize and contribute to Anemoi, a toolbox designed for the implementation of AI tools for weather and climate applications, developed by the European Center for Medium-range Weather Forecast (ECMWF).

Another important objective of this project is to assess the integration of these systems into operational forecasting services, ideally complementing numerical and statistical models currently used at MeteoSwiss and potentially at other European Weather Services.

The candidate is expected to engage in regular meetings and updates with relevant stakeholders, including MeteoSwiss and other EUMETNET members and advisory committees.

Main Duties and Responsibilities

• Collect and streamline data products in collaboration with MeteoSwiss and relevant European data providers, coding a dedicated anemoi-dataset parsing routine for efficient training and inference purposes.
• Review and implement baselines and state-of-the-art methods relevant to the task, providing critical assessments.
• Collaborate with MeteoSwiss scientists and engineers to develop weather forecasting models that are core to this project.
• Implement assessment and verification tools, interpret results, and communicate relevant findings to stakeholders.
• Complement and contribute to the ANEMOI library where applicable (e.g., baselines, assessments, custom methods, and functionalities).
• Proactively engage with the relevant community.

Qualifications

We are looking for a motivated early-career scientist who has completed an MSc thesis in a relevant field.

• A Master's degree in computer science, machine learning, data science, or a related area, with experience in geospatial data, weather data, or climate data.
• Familiarity with both traditional and modern machine learning techniques, from training random forests to transformer graph neural networks; experience with the latter is a plus.
• Strong motivation to thrive in a dynamic research environment committed to an exciting project.
• A solid understanding of recent literature and advancements in the field.
• Proficient in Python coding and experienced in large collaborative and open-source codebases. Familiarity with Git and best practices for multidisciplinary and scientific code collaboration is preferred.
• Familiarity with tools such as PyTorch, PyTorch-Lightning, Hydra, Zarr, Xarray, and Earthkit is advantageous.
• Experience in scientific research, including skill in presenting results succinctly to both scientific and non-scientific audiences.
• A history of working in diverse interdisciplinary teams.
• Eagerness to engage in an agile working environment.

Benefits

• A stimulating, collaborative, cross-disciplinary environment at a world-class research institution, working alongside 40 data scientists from over 15 different countries.
• Close collaboration with a dedicated ML team at MeteoSwiss, including regular visits to their main office at Zurich Airport.
• A supportive work-life balance, with flexibility for home-office workdays.
• A travel budget for attending events and conferences.
• Opportunities for publishing research in top-tier journals and conferences through collaboration with experts across varying fields.
• The chance to supervise student projects.
• Encouragement for experimentation and innovation, with active support for learning new technologies and approaches on the job.
• Your insights and opinions will always be valued.
• Salary is in accordance with ETH Zurich regulations.

We look forward to receiving your online application using the form below.

For further information about our project partners, please visit the Swiss Data Science Center, EUMETNET, and MeteoSwiss websites.

Questions regarding the position should be directed to Michele Volpi at michele.volpi@sdsc.ethz.ch (no applications).

Please note that only applications matching the job profile will be considered.