Publisher
source

Université Savoie Mont-Blanc

Post-Doctoral Position in AI-Based Avalanche Detection and Sensor Domain Adaptation Université Savoie Mont Blanc in France

Degree Level

Postdoc

Field of study

Computer Science

Funding

Full funding available

Deadline

December 31, 2026
Country flag

Country

France

University

Université Savoie Mont-Blanc

Social connections

How do I apply for this?

Sign in for free to reveal details, requirements, and source links.

Apply for this position

Continue to application

Keywords

Computer Science
Environmental Science
Deep Learning
Data Fusion
Artificial Intelligence
Image Processing
Computer Vision
Python Programming
Anomaly Detection
Domain Adaptation
Wireless Sensor Network
Statistics
Machine learning

About this position

The Université Savoie Mont Blanc (USMB) and the LISTIC laboratory invite applications for a postdoctoral position as part of the RESIL-AV project, which aims to advance avalanche detection using state-of-the-art Artificial Intelligence (AI) techniques. The project builds on preliminary work at the Bessans site in Haute-Maurienne, where high-resolution imagery has enabled the identification of avalanche characteristics. However, current methods face challenges such as sensitivity to weather and lighting, and difficulties in generalizing models to new sites and sensor types.

The RESIL-AV project seeks to overcome these limitations by integrating a network of heterogeneous sensors, including lower-resolution webcams, directional acoustic sensors, and meteorological stations distributed across the Alps. This multi-sensor approach will enhance detection accuracy and robustness, allowing for validation and correlation of avalanche events across different data sources. The project will address key AI challenges, particularly domain adaptation—transferring knowledge from models trained on one domain (e.g., high-resolution images) to others (e.g., webcam images or different mountain sites).

Graph-based learning will be a central methodology, representing sensors as nodes and their relationships (spatial or statistical) as edges. This approach enables modeling complex interactions and improving detection performance. The postdoctoral fellow will study and implement adaptation strategies for various sensors and mountain sites, starting with an evaluation of existing neural architectures on diverse datasets. Subsequent phases will involve developing domain adaptation strategies, constructing relationship graphs, and assessing the benefits of graph-structured learning. Depending on the candidate’s expertise, additional methods such as multi-modal autoencoders for data fusion or anomaly detection may be explored.

Applicants must hold a Ph.D. in Deep Learning, Statistics, or a related field, with solid experience in image processing and/or data analysis. Proficiency in Python programming is essential. The position is full-time and based at the LISTIC laboratory in Chambéry, France. Internal application forms may be required as part of the submission process.

The application deadline is 5 May 2026, with the position expected to start on 1 June 2026. For further information, visit USMB’s website or the Euraxess position page. Applications can be submitted via email to [email protected] or through the Euraxess portal. For inquiries, contact [email protected].

Funding details

Full funding including tuition fees and living expenses is available for this position. The scholarship covers all educational costs and provides a monthly stipend.

How to apply

Please submit your application including a cover letter, CV, academic transcripts, and contact information for two references. Applications should be sent via the online portal before the deadline.

More information can be found here

Ask ApplyKite AI

Start chatting
Can you summarize this position?
What qualifications are required for this position?
How should I prepare my application?