> Markdown version of [/jobs/ext/1904578-doctorant-f-h](https://www.wearedevelopers.com/jobs/ext/1904578-doctorant-f-h). 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). --- # Doctorant F/H - **Company:** Inria - **Location:** Montbonnot-Saint-Martin, France (Remote available) - **Experience:** Experienced - **Salary:** €27,600.0 - **Contract:** Temporary contract - **Skills:** Agile Methodology, Python (Programming Language), Metadata, Language Modeling - **Published:** August 3, 2026 - **Apply:** https://jobs.inria.fr/public/classic/fr/offres/2026-10360 ## About the Role Compétences techniques et niveau requis : Python, librairies d'apprentissage profond Langues : français courant, anglais C1 au minimum. Compétences relationnelles : excellent niveau en communication écrite et oral Compétences additionnelles appréciées, * formation en sciences des données * première expérience de la recherche en intelligence artificielle (6 à 18 mois) ## Description The aim is to enhance and complement the use of remote sensing data archives via the combination of such data with textual and/or metadata information associated to the image scene or to the particular geographical area covered by the satellite data. To this purpose, research activities will be conducted on vision-language models tailored for the remote sensing field with a particular emphasis on the available CNES data archive. PhD topic : Text/Metadata supervision for learning representations of satellite images. Within satellite imagery, metadata such as ground sample distance, off-nadir viewing angle, time and location hold significant semantic information that improves scene understanding. Recent literature [Bourcier24] demonstrated that jointly combining remote sensing image data and their corresponding metadata allows to learn effectively representation capable to improve performances on downstream recognition tasks. In this project we propose to make a step further investigating how metadata can be used to learn large foundation models in the framework of the exploitation of large image archives of optical data. This task could leverage Pleiades (image and metadata) datasets. In the frame of self-supervised learning, temporal contrastive learning is a simple way to construct a very high number of positive pairs. Another idea is to also leverage geographic metadata [Ayush21] in order to construct contrastive pairs, hence driving improved feature learning that will account for regional characteristics while foundation models are trained using data with a global coverage. Large foundation models benefit from learning across multiple modalities and multiple tasks. Metadata may be used to address such situations by providing auxiliary labels (e.g., season, time of day, sensor name). The model can take metadata as an additional input (e.g., time + location embedding). Metadata can be directly combined with visual features in a cross-modal architecture (e.g., using vision transformers with tabular inputs). Finally, models may generalize better across domains (sensor, location, season) by encoding domain-relevant metadata., Travail de thèse: * recherche bibliographique * proposition de méthodes et mise en oeuvre des choix effectués en accord avec la direction de la thèse * tests et validation des résulatts avec les données fournies par le CNES * dissémination des résultats par des publications * participation à la vie de l'équipe (participation aux séminaires etc.) * rédaction du mémoire de thèse et soutenance ## Related Videos - [Carl Lapierre - Exploring Advanced Patterns in Retrieval-Augmented Generation](https://www.wearedevelopers.com/videos/1235-carl-lapierre-exploring-advanced-patterns-in-retrieval-augmented-generation) - [A Data Mesh needs Open Metadata](https://www.wearedevelopers.com/videos/505-a-data-mesh-needs-open-metadata) - [ShapeShift: Reinventing Agile for a B2B SaaS Scale-Up](https://www.wearedevelopers.com/videos/1655-shapeshift-reinventing-agile-for-a-b2b-saas-scale-up) - [Unveiling the Magic: Scaling Large Language Models to Serve Millions](https://www.wearedevelopers.com/videos/1619-unveiling-the-magic-scaling-large-language-models-to-serve-millions) - [Graphs and RAGs Everywhere... But What Are They? - Andreas Kollegger - Neo4j](https://www.wearedevelopers.com/videos/1311-graphs-and-rags-everywhere-but-what-are-they-andreas-kollegger-neo4j) - [AI in the Open and in Browsers - Tarek Ziadé](https://www.wearedevelopers.com/videos/1787-ai-in-the-open-and-in-browsers-tarek-ziade) ## Related Articles - [The 13 Best Python Libraries for Developers in 2025](https://www.wearedevelopers.com/magazine/371-the-13-best-python-libraries-for-developers-in-2025) - [How to Become an AI Engineer](https://www.wearedevelopers.com/magazine/331-how-to-become-an-ai-engineer) - [7 good reasons why you should learn Python in 2021](https://www.wearedevelopers.com/magazine/19-7-good-reasons-why-you-should-learn-python-in-2021) - [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) - [Best Coding Boot Camps in Germany](https://www.wearedevelopers.com/magazine/237-best-coding-boot-camps-in-germany) - [AI overspill Dec 2026: AI in a JAM, Blocking AI browsers, learning programming languages ](https://www.wearedevelopers.com/magazine/673-ai-overspill-dec-2026-ai-in-a-jam-blocking-ai-browsers-learning-programming-languages)