Job offer

Inria
Villeneuve-d'Ascq, France
1 day ago
Apply on jobs.inria.fr
Prepare application

Role details

Contract type
Temporary contract
Employment type
Full-time (> 32 hours)
Working hours
Regular working hours
Languages
English, French
Job source

Tech stack

Artificial Intelligence Distributed Systems Machine Learning Open Source Technology Open Access Differential Privacy

Job 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

Requirements

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

Benefits & conditions

  • Subsidized meals
  • 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

According to profile Selection process

Apply for this position

This job is hosted externally. Click below to view the full posting and apply.

Apply on jobs.inria.fr
Prepare application

Good distractions

Loading talks and stories from around this role…