Software engineer on private and decentralized machine learning (H/F)

The  Inria University of Lille centre, created in 2008, employs 360 people  including 305 scientists in 15 research teams. Recognised for its strong  involvement in the socio-economic development of the Hauts-De-France  region, the Inria University of Lille centre pursues a close  relationship with large companies and SMEs. By promoting synergies  between researchers and industrialists, Inria participates in the  transfer of skills and expertise in digital technologies and provides  access to the best European and international research for the benefit  of innovation and companies, particularly in the region.For more  than 10 years, the Inria University of Lille centre has been located at  the heart of Lille's university and scientific ecosystem, as well as at  the heart of Frenchtech, with a technology showroom based on Avenue de  Bretagne in Lille, on the EuraTechnologies site of economic excellence  dedicated to information and communication technologies (ICT)

The position will be supported by FedMalin, a collaborative project on Federated Learning between 11 teams at INRIA. The project addresses FL challenges when deployed over the internet (privacy, heterogeneity, energy, fairness, ...) and has medicine as a main targeted application domain.

FedMalin develops several software tools, including the open source library DecLearn (https://gitlab.inria.fr/magnet/declearn/declearn2) for private and decentralized/federated machine learning and data analysis. The hired engineer will contribute to the ongoing development of DecLearn, expanding its capabilities with new algorithms and enhanced functionalities.

The activities will include interactions with the members of the project, the Magnet and Premedical teams (researchers and engineers). We also expect to conduct multi-centric medical studies across several hospitals.  The activities can also include travel, e.g., to conferences to demonstrate the developed library and to contribute to the community building effort.

• Consolidate and extend the existing library for decentralized and privacy-preserving machine learning developed in the project
• Deploy the library in real-world conditions and experiment on synthetic and (benchmark) medical data, analyzing the benefits and the costs compared to a centralized approach.
• Publish open source code and integrate in existing libraries
• Publish scientific results in medical and computer science conferences

The Declearn project is available at https://gitlab.inria.fr/magnet/declearn/declearn2

• Implement federated and privacy-preserving algorithms for machine learning
• Experiment with medical partners on multicentric medical studies
• Evaluation of results
• Reporting, disseminating and presenting results

• Programming skills in Python, including object oriented programming, unit testing, documentation writing, deployment tools, asynchronous programming and networking.
• Good understanding of scientific papers on machine learning.
• Interest for machine learning and medical applications. 
• Good communication skills; communication and animation of software development communities, git workflow

• 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