PhD in Multimodal AI for Humanitarian Relief

École polytechnique fédérale de Lausanne, EPFL; Mittelwallis; Vor Ort; CHF 60.000 - 85.000; Vollzeit

Benefits dieser Stelle

Competitive remuneration

Educational opportunities at EPFL-Val‑

International conference participation

Zusammenfassung

EPFL, the Swiss Federal Institute of Technology in Lausanne, invites applications for a full-time PhD position at ENAC Faculty in Sion. You will develop cross-modal AI for humanitarian relief, linking satellite imagery with textual data and exploring vision-language models to support situational awareness and evidence-informed response.

You will publish findings, collaborate with ETH and ICRC, and participate in international conferences, while contributing to ENAC education.

Qualifikationen

• Master's degree in computer science.
• Experience with humanitarian sector and/or remote sensing.
• Proficiency in Python coding and deep learning frameworks.
• Fluent in English.
• Motivated, curious, and able to work in a dynamic team.

Aufgaben

• Design multimodal deep learning methodologies linking satellite image and textual data about conflicts.
• Develop localization for events with robustness across domains.
• Create visualization and data analysis tools with ICRC colleagues.
• Write publications.
• Attend international conferences in ML and remote sensing.
• Participate in ENAC faculty educational activities.

Kenntnisse

Python programming

Deep learning

English fluency

Ausbildung

Master's degree in computer science

Tools

Python

Jobbeschreibung

EPFL, the Swiss Federal Institute of Technology in Lausanne, invites applications for a full-time PhD position at ENAC Faculty in Sion. You will develop cross-modal AI for humanitarian relief, linking satellite imagery with textual data and exploring vision-language models to support situational awareness and evidence-informed response.

You will publish findings, collaborate with ETH and ICRC, and participate in international conferences, while contributing to ENAC education.