> Markdown version of [/jobs/ext/4765040-job-offer](https://www.wearedevelopers.com/jobs/ext/4765040-job-offer). 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). --- # Job offer - **Company:** Inria - **Location:** Villeneuve-d'Ascq, France (Remote available) - **Contract:** Temporary contract - **Skills:** Artificial Intelligence, Distributed Systems, Machine Learning, Open Source Technology, Open Access, Differential Privacy - **Published:** November 18, 2026 - **Apply:** https://jobs.inria.fr/public/classic/en/offres/2026-10715 ## About the Role Technical skills : * Knowledge of distributed systems, cryptography, statistical privacy * Writing and presentation skills * Research creativity Languages : * Mastering English is essential Relational skills : * smoothly working in a team in a reseach environment * effective communication and collaboration * eager to learn in an academic setting Specific Requirements We are looking for a candidate with strong research experience in privacy-preserving federated machine learning. It is a plus to have good knowledge of topics such as secret sharing, homomorphic encryption, differential privacy, byzantine failures and distributed systems. It is important to integrate in the academic setting where everybody is continuously learning, in the team where collaboration is important and in the project with its specific goals and partners. Languages FRENCH ## Description This post-doc position will be supported by the PEPR IA Redeem project. While this position will be in the MAGNET team in Lille, we will collaborate with the several project partners. While AI techniques are becoming ever more powerful, there is a growing concern about potential risks and abuses. As a result, there has been an increasing interest in research directions such as privacy-preserving machine learning, explainable machine learning, fairness and data protection legislation. Privacy-preserving machine learning aims at learning (and publishing or applying) a model from data while the data is not revealed. Notions such as (local) differential privacy and its generalizations allow to bound the amount of information revealed. The MAGNET team is involved inthe related TRUMPET, FLUTE and REDEEM projects, and is looking for team members who can in close collaboration with other team members and national & international partners contribute to one or more of these projects. The recruited post-doctoral researcher will collaborate with colleagues in the MAGNET team and the REDEEM project. In particular, the work will contribute to REDEEM's research. By default all published work will be open access and developed software will be open-source. Tasks may include * Researching new algorithms for scalable robust decentralized machine learning. * Researching new theory to better analyze decentralized systems and the performance of decentralized AI algorithms. * Studying new algorithms for reasoning about data privacy * Developing new theory on secure aggregation, privacy and robustness in decentralized systems * Publishing articles describing these results and presenting them. * Collaborate with project partners on related topics