EPFL, l’École polytechnique fédérale de Lausanne, est l’un des campus universitaires les plus dynamiques d’Europe et s’inscrit dans le top 20 mondial de nombreux classements académiques. L’EPFL compte plus de 6'500 membres du personnel qui font vivre les trois missions principales de l’École : l’éducation, la recherche et l’innovation. Le campus de l’EPFL offre un cadre de travail exceptionnel au cœur d’une communauté de plus de 18'500 personnes, dont près de 14'000 étudiant·e·s et 4'000 chercheur·euse·s issu·e·s de plus de 120 nationalités différentes.

PhD position: cross modal AI for humanitarian relief efforts

Your mission

We are offering a challenging position as a full-time (100%) PhD Student at ENAC Faculty at EPFL, Sion.

 

As a PhD student, you will develop technology for humanitarian data mining and analysis in the framework for the project CARE (Cross-modal AI for Relief Efforts), a collaborative project between EPFL, ETH and the ICRC. 

 

You will innovate in foundational methods for jointly modelling satellite imagery and textual conflict data. Advances in vision-language representation learning will be explored to link the two sources of information through alignment pipelines, localisation models, and damage detection with contextual priors. Working in close interaction with colleagues at ETH and the ICRC, you will create new capabilities directly aligned with the ICRC's priorities in situational awareness and evidence-informed response and propose operational tools.

Main duties and responsibilities include

  • Design multimodal deep learning-based methodologies linking satellite image and textual data about conflicts.
  • Develop approaches for events localization, with emphasis on robustness across events (domain adaptation).
  • Develop tools for visualization and data analysis together with colleagues at the ICRC.
  • Write publications.
  • Attend international conferences, both in machine learning and remote sensing.
  • Participate in the educational activities of the ENAC faculty.

Your profile

  • You have a master’s degree in computer science.
  • You have experience with the humanitarian sector and/or in remote sensing.
  • You are proficient in Python coding and deep learning frameworks.
  • You are fluent in English.
  • You are motivated, curious, and willing to work in a highly dynamic team.

We offer

  • An opportunity to develop a scientific career in an exciting area of science. 
  • A unique opportunity to learn high-end techniques and approaches.
  • Excellent educational conditions and competitive remuneration.
  • A multi-cultural and stimulating scientific environment, in the EPFL-Valais campus in Sion

How to apply

The selection process involves multiple stages, and short-listed candidates will be requested to apply to a specific EPFL Doctoral Program to qualify for a PhD. Please check this page for additional information on admission. Please note that this is a separate application process necessary to be eligible to complete your PhD at EPFL.

 

To apply, please use the application link on this page. Please apply before October 1st, 2026.

 

Your application must contain:

  1. A letter of interest explaining your motivation for the project and skills (max. 2 pages)
  2. An updated CV 
  3. Contact details of 3 reference persons.
  4. Scans of your diplomas and grades from all academic institutions of higher education (after and not including high-school) listed in your CV. If you do not yet have your Master’s diploma, please send a certificate issued by your current institution of higher education that confirms your enrolment in a Master’s program).
  5. Copy of your passport or official identity document.
  6. (optional) a sample of your published work (if available), Master’s thesis or semester project.

Contract Start Date: 01/01/2027

Activity Rate : 100,00

Contract Type: Doctorant·e

Duration: 1 year (candidacy examination) + up to 5 years after

Reference: 2409

 

For more information, please contact: devis.tuia@epfl.ch









Seul·es les candidat·e·s ayant postulé via le site internet de l'EPFL ou celui de notre partenaire Jobup seront pris en compte. Les dossiers transmis par les agences non mandatées ne seront pas pris en compte.