> Markdown version of [/jobs/ext/77643-post-doctoral-research-visit-f-m-learning-crowd-dynamics-from-real-world-data](https://www.wearedevelopers.com/jobs/ext/77643-post-doctoral-research-visit-f-m-learning-crowd-dynamics-from-real-world-data). Every page supports `.md` or `Accept: text/markdown`. Links point to the HTML versions so they work for humans too. Agent guide: [/agents.md](https://www.wearedevelopers.com/agents.md). --- # Post-Doctoral Research Visit F/M Learning crowd dynamics from real-world data - **Company:** Inria - **Location:** Rennes, France (Remote available) - **Salary:** €33,456.0 - **Contract:** Permanent contract - **Skills:** C++ (Programming Language), Computer Graphics, Python (Programming Language), Machine Learning, Pytorch, Transfer Learning, Deep Learning, Generative AI, Data Analytics - **Published:** May 26, 2026 - **Apply:** https://fr.indeed.com/viewjob?jk=20d4034fb6450211 ## About the Role Do you have experience in Statistics?, Do you have a Doctoral degree?, * Deep learning, in particular generative models and/or imitation learning * Programming in Python (PyTorch or equivalent) * Experience in trajectory prediction, motion modelling, or human behaviour analysis Technical skills (a plus): * Background in crowd simulation or collective behaviour modelling * Experience with C++ for simulation development * Familiarity with evaluation metrics for trajectory prediction (ADE, FDE) Languages: * English (required for scientific dissemination) Relational skills: * Autonomy and scientific initiative in an exploratory research context * Ability to work in a collaborative and interdisciplinary environment * Good communication skills for regular interactions with the data acquisition team, A strong background in machine learning and a genuine interest in its application to the modelling of physical or social systems are the natural profile for this position. We also welcome candidates with a background in computer graphics or character animation who have developed expertise in data-driven approaches to motion modelling. The position requires intellectual curiosity, the ability to work with limited and imperfect data, and a taste for bridging the gap between real-world observations and simulation. A collaborative mindset is essential, as the modelling work is tightly coupled to the data acquisition activities of PDoc 1 - the nature and quality of the available data will directly shape the modelling choices. ## Description Collaboration: The recruited person will work in close connection with the first postdoctoral researcher of the FOUL-X project, who is responsible for building the field dataset that will serve as the primary input for the modelling work. The postdoc will also interact regularly with a PhD student of the team developing the pedestrian tracking pipeline, whose outputs feed directly into the learning process. This close collaboration ensures that modelling choices are informed by the nature and constraints of the available data, and reciprocally, that data acquisition is guided by the requirements of the learning approaches. Responsibilities: The person recruited is responsible for the design, implementation and evaluation of machine learning models for crowd dynamics, working with the dataset progressively built during the project. The recruited person will take initiatives in exploring a range of modelling paradigms - including generative models, imitation learning, or physics-informed approaches - and will contribute to defining evaluation metrics adapted to the specific challenge of assessing the diversity of learned crowd dynamics. Steering/Management: The person recruited will be in charge of the modelling and learning activities of the FOUL-X project, from the initial design of data representations and learning architectures to the evaluation and dissemination of results at major scientific venues. Principales activités Phase 1 - Architecture design and preliminary learning (months 1-6) * Conduct a targeted review of existing approaches for data-driven crowd dynamics modelling, covering trajectory prediction, generative models, imitation learning, and physics-informed approaches * Define crowd data representations suited to machine learning, combining individual (positions, velocities), collective (density, flow), and environmental (obstacles, spatial layout) information * Select and implement the most promising learning architecture for crowd dynamics modelling, based on pre-existing datasets available in the team * Validate the technical functioning of the learning pipeline and establish baseline performance metrics Phase 2 - Learning diverse crowd dynamics from FOUL-X data (months 7-24) * Develop and iteratively refine machine learning models for crowd dynamics using the dataset progressively built by PDoc 1 across multiple acquisition sites * Address the challenges of learning from limited and partially observable real-world data, exploring techniques such as transfer learning, data augmentation, and weak supervision * Demonstrate the capacity of the models to capture and distinguish diverse crowd dynamics, as observed across different sites, populations, and spatial configurations * Contribute to the definition of evaluation metrics adapted to the assessment of diversity in learned crowd dynamics, in collaboration with PDoc 1 * Disseminate results at major scientific venues (IEEE CVPR, ACM SIGGRAPH, PED 2027) ## Related Videos - [Getting Started with Machine Learning](https://www.wearedevelopers.com/videos/260-getting-started-with-machine-learning) - [Geometric deep learning for drug discovery](https://www.wearedevelopers.com/videos/264-geometric-deep-learning-for-drug-discovery) - [Hacking Your Vacation: Using Data for Fun](https://www.wearedevelopers.com/videos/585-hacking-your-vacation-using-data-for-fun) - [Photonic Computing: Programming a New Class of AI Accelerators (incl. Live Coding)](https://www.wearedevelopers.com/videos/100196-photonic-computing-programming-a-new-class-of-ai-accelerators-incl-live-coding) - [Your imaginations is (no longer) the limit: how Generative AI empowers people to be creative](https://www.wearedevelopers.com/videos/741-your-imaginations-is-no-longer-the-limit-how-generative-ai-empowers-people-to-be-creative) - [Serverless deployment of (large) NLP models ](https://www.wearedevelopers.com/videos/158-serverless-deployment-of-large-nlp-models) ## Related Articles - [Dev Digest 121 - AI goes offline](https://www.wearedevelopers.com/magazine/456-dev-digest-121-ai-goes-offline) - [Résumé-Driven Development: How IT trends affect the job market for software developers](https://www.wearedevelopers.com/magazine/59-resume-driven-development-how-it-trends-affect-the-job-market-for-software-developers) - [Dev Digest 138 - Are you secure about this?](https://www.wearedevelopers.com/magazine/486-dev-digest-138-are-you-secure-about-this) - [Top 6 Hackathons for Developers in 2023](https://www.wearedevelopers.com/magazine/263-top-6-hackathons-for-developers-in-2023) - [How to Become an AI Engineer](https://www.wearedevelopers.com/magazine/331-how-to-become-an-ai-engineer) - [Guide for Expats Living in France](https://www.wearedevelopers.com/magazine/305-guide-for-expats-living-in-france)