Inria, the French national research institute for the digital sciences
Organisation/Company: Inria, the French national research institute for the digital sciences
Research Field: Computer science
Researcher Profile: Recognised Researcher (R2)
Country: France
Application Deadline: 30 Dec 2024 - 23:00 (UTC)
Type of Contract: Temporary
Job Status: Full-time
Hours Per Week: 38.5
Offer Starting Date: 1 May 2024
Is the job funded through the EU Research Framework Programme? Horizon 2020
Reference Number: 2024-07160
Is the Job related to staff position within a Research Infrastructure? No
Offer Description This post-doctoral position will be supported by the HE Trumpet project, the HE Flute project, and/or the PEPR IA Redeem project. While this position will be in the MAGNET team in Lille, we will collaborate with several European project partners.
As AI techniques become more powerful, there is a growing concern about potential risks and abuses. This has led to increased interest in research directions such as privacy-preserving machine learning, explainable machine learning, fairness, and data protection legislation.
Privacy-preserving machine learning aims to learn (and publish or apply) a model from data while the data is not revealed. Notions such as (local) differential privacy and its generalizations allow us to bound the amount of information revealed.
The MAGNET team is involved in the 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. All of these projects aim at researching and prototyping algorithms for secure, privacy-preserving federated learning in settings with potentially malicious participants. The TRUMPET and FLUTE projects focus on applications in the field of oncology, while the REDEEM project has no a priori fixed application domain.
The start and end date of the offered post-doctoral positions can be negotiated, subject to the administrative constraints that they start at the earliest on 1/5/2024 and end before or around 30/04/2026, and that individual contracts last no longer than 2 years.
The recruited post-doc will collaborate with colleagues in the MAGNET team and the TRUMPET, FLUTE, and REDEEM project consortia.
If the research features a prototype, it will contribute to the project's open-source library.
We hope the post-doc can bring new expertise to the group and/or help intensify collaboration in the project consortium. He will collaborate closely with other group members on realizing the research objectives of the project. Engineers in the team can support the prototyping and validation.
Possible topics of research include (but are not limited to):
Cryptography-based strategies to improve the security of privacy-preserving AI systems.
Inference methods for privacy assessment and/or theory for statistical privacy in general.
Programming language strategies relevant in compilers and interpreters.
Design and development of the TRUMPET/FLUTE platform and its supporting algorithms.
Contribute to the research of the projects.
Collaborate with other MAGNET and project team members.
Collaborate with engineers to prototype proposed algorithms and validate them.
The following skills are desired for this position:
A strong research background in the domain of the project (or at least a specific area such as privacy, cryptography, statistics, distributed systems, etc.).
Good communication and reporting skills, and an interest in collaborative work.
Proficiency in English.
Specific Requirements We are looking for a candidate with a strong background in computer science, with interest in the multiple challenges related to privacy and an approach involving several specializations (e.g., machine learning, security, cryptography, compilation).
Candidates should provide sufficient information to support their application. The page https://team.inria.fr/magnet/how-to-apply/ lists the minimum information desired (which is more than what is strictly required by the online submission platform).
Languages
FRENCH: Level Basic
ENGLISH: Level Good
Additional Information Partial reimbursement of public transport costs.
Leave: 7 weeks of annual leave + 10 extra days off due to RTT (statutory reduction in working hours) + possibility of exceptional leave (sick children, moving home, etc.).
Possibility of teleworking and flexible organization of working hours.
Professional equipment available (videoconferencing, loan of computer equipment, etc.).
Social, cultural, and sports events and activities.
Access to vocational training.
Social security coverage.
Gross monthly salary (before taxes): 2,788 €
Selection Process CV + application letter + recommendation letters + list of publications.
Academic transcripts, thesis, project report.
#J-18808-Ljbffr