Research engineer - Machine Learning (RE1) per al Barcelona Supercomputing Center

We are seeking a highly motivated Research Engineer with expertise in machine learning, data science, or computational environmental sciences to contribute to cutting-edge research in Earth Sciences.

The selected candidate will play a key role in developing and optimizing machine learning workflows for large-scale land-use, land-cover, and Leaf Area Index (LAI) reconstruction, supporting both historical and future climate scenarios.

This position involves integrating deep learning models, refining data workflows, and contributing to predictive modeling efforts within multiple European projects, including TerraDT and CONCERTO. It builds upon methodologies established in the CERISE project and aims to generate high-resolution, temporally extended datasets to improve climate model simulations and advanced Earth system modeling capabilities.

This role provides a unique opportunity to work with an interdisciplinary team of machine learning researchers and climate scientists. The team will focus on developing scalable solutions for processing and analyzing high-dimensional environmental data. The selected candidate will also contribute to scientific publications, project documentation, and technical reporting, collaborating on research efforts within international projects.

Key Duties

  • Develop and optimize large-scale machine learning workflows for Earth Science applications, focusing on land-use, land-cover, and LAI downscaling for both historical and future scenarios.
  • Implement and evaluate deep learning architectures for predictive modeling of land-use, land-cover, and climate-related variables, while developing model evaluation methodologies, including visualization and validation tools to compare deep learning models with traditional baselines.
  • Refactor and modularize existing machine learning pipelines to improve scalability, efficiency, and deep learning integration.
  • Work with large geospatial datasets (NetCDF, Zarr) and optimize data processing workflows for high-performance computing (HPC) environments.
  • Ensure that reconstructed land-use, land-cover, and LAI datasets align with Earth system modeling requirements.
  • Participate in scientific publications and technical reporting, contributing to documentation, with opportunities to be involved in academic publications and project reporting.

Data de tancament: Dilluns, 24 Març, 2025

Més informació

Més posts de Recerca

Entrada destacada

Properes activitats. Serveis gratuïts per a alumnat i alumni de la UPC

Entrevistes d'assessorament Reserva la teva cita En línia Presencial Biblioteca Rector Gabriel Ferraté Presencial EEBE Presencial ETSEIB...