Junior researcher in computer science for climate risk modelling
Pubblicato il 22-08-2026 - Altro in Bolzano
Center for Climate Change and Transformation
Short description of the position:
We are looking for a motivated researcher/computer scientist to join the Climate and Disaster Risk (CDR) research group within the Center for Climate Change and Transformation (CCT). The successful candidate will develop data-driven methods that transform large climate and natural-hazard datasets into robust, interpretable information for climate-risk assessment, impact forecasting and early warning. The position combines applied machine learning and AI research with operational implementation, and it is conducted in a close collaboration across climate science, natural hazards, Earth observation, geospatial analysis and risk management.
The activities will be primarily conducted in the framework of the EU-funded project AlpFuturePaths which focuses on the elaboration of future climate-related hazard scenarios and risks in the Alpine environment. However, the successful candidate is expected to contribute to other ongoing projects and research group activities related to climate risk assessment and prediction.
Tasks:
Develop and evaluate machine-learning and deep-learning methods for detecting and predicting climate extremes, natural hazards and related risks in Alpine regions.
Process and analyse large climate, Earth-observation and geospatial datasets for forecasting, classification and pattern recognition.
Contribute to impact forecasting, early-warning and decision-support systems, including validation, uncertainty assessment and communication of risk information
Collaborate with interdisciplinary teams, international partners and local experts, including the Civil Protection Agency of the Autonomous Province of Bolzano/Bozen.
Requirements:
Master’s degree in computer science, statistics, geoinformatics, climate or environmental sciences, natural hazards or a comparable field.;
First experience in machine learning and statistical modelling; interest in deep learning and AI research f