Postdoc: Data-Driven Crowd Dynamics & ML Research

1000scholars; Rennes; On-site; EUR 40,000 - 48,000; Full time

Job summary

VirtUs team at the Inria Centre in Rennes invites applications for a postdoctoral position to develop ML models that learn crowd dynamics from real-world field data. Under supervision, you will design learning-based models including generative or imitation learning to capture diverse crowd behaviors across sites.

This project aims to deliver adaptive crowd simulators and contribute to data-driven methods in pedestrian dynamics. Collaboration with data acquisition teams is required.

Qualifications

• PhD in computer science or a related field.
• Strong background in deep learning and ML for dynamic systems.
• Experience with Python and PyTorch.
• Experience in trajectory prediction or human behaviour analysis.
• Ability to work in interdisciplinary team.

Responsibilities

• Design, implement and evaluate ML models for crowd dynamics.
• Work with field data and multiple acquisition sites.
• Explore generative models, imitation learning, and physics-informed approaches.
• Define evaluation metrics for diversity of learned dynamics.
• Disseminate results at major scientific venues.

Skills

Deep learning

Python / PyTorch

Trajectory prediction

Human behaviour analysis

Education

PhD in Computer Science or related field

Tools

PyTorch

C++

Job description

VirtUs team at the Inria Centre in Rennes invites applications for a postdoctoral position to develop ML models that learn crowd dynamics from real-world field data. Under supervision, you will design learning-based models including generative or imitation learning to capture diverse crowd behaviors across sites.

This project aims to deliver adaptive crowd simulators and contribute to data-driven methods in pedestrian dynamics. Collaboration with data acquisition teams is required.