By continuing to browse the site, you are agreeing to our use of cookies. (More details)
Portal > Offres > Offre UMR5220-FRECER-001 - Expert (H/F) en déployement d'applications deep learning sur des données COVID

Expert (M/F) in deploying deep learning applications on COVID data

This offer is available in the following languages:
Français - Anglais

Ensure that your candidate profile is correct before applying. Your profile information will be added to the details for each application. In order to increase your visibility on our Careers Portal and allow employers to see your candidate profile, you can upload your CV to our CV library in one click!

Faites connaître cette offre !

General information

Reference : UMR5220-FRECER-001
Date of publication : Monday, July 27, 2020
Type of Contract : FTC Technical / Administrative
Contract Period : 6 months
Expected date of employment : 22 September 2020
Proportion of work : Full time
Remuneration : between 2500 et 3000€ gross
Desired level of education : Engineer
Experience required : 1 to 4 years


In the current context of COVID-19, many national and international initiatives have been carried out to respond to tasks of automatic diagnosis of the disease by artificial intelligence methods, particularly using CTscan images. CT-scans are currently the most reliable source of information for diagnosis and are becoming the reference examination. The approaches used rely on deep convolutional neural networks to segment the lungs and lesions in CT-scan images, and rely on an estimate of the relative size of the lesion to determine the level of severity of contagion.
Within the COVID-19 working group of the ISIS GoR, action is being taken on the implementation of artificial intelligence methods for the prognosis of disease progression. This presents major clinical challenges in the current context of deconfinement and in the perspective of a second wave of contamination. The objective is to take an additional step in prediction, in particular to detect among the contaminated patients those at risk of contracting a serious version of the disease requiring, if necessary, a place in intensive care.


The applicant's mission will be to set up a platform open to national public laboratories involved in this action. This platform will allow secure access and deployment of learning algorithms from an innovative database. Given that this database contains sensitive but anonymised patient information (several types of CT acquisition + patient file), it is essential to guarantee the legal and regulatory framework surrounding access to the data (labelled server for storage of medical data / RGPD etc.). The data cannot transit on calculation nodes outside the laboratory without the risk of breaking the traceability of the use of this data. It is therefore necessary to use the laboratory's GPU-related computing resources. Under the supervision of the engineers of the IT and development department, the candidate will have to ensure the deployment of algorithms (via container technologies) on the calculation servers which alone will have access to patient data. A monitoring and control infrastructure must be set up to ensure a sufficient level of service for a research use (rapid evolution of scripts, complex AI method). This essential porting and administration of these scripts will require the candidate to have an advanced involvement in deep learning algorithms in order to detect problems upstream.
Moreover, this approach could be extended to federated learning methods. If new sources of distributed data (e.g. PACS or warehouses from different clinical centres) become available, the models are then trained on several sites and the only learning result is shared respecting the personal nature of the medical data. These developments also require a significant effort on monitoring and human resources at each data-providing site.


The candidate will have an extremely strong foundation in the use of containers and the use of deep learning libraries. Indeed, his primary role is the support and deployment of deep learning scripts.
- Programming languages: Python, Javascript,
- Technologies: Kubernetes, Container services
- Specific bookshops: Torchmed, pyTorch

Work Context

The position is open in the CREATIS laboratory (Centre de Recherche en Acquisition et Traitement de l'Image pour la Santé) CNRS Unit UMR 5220.

The Creatis laboratory is a Medical Imaging Research Unit with a staff of about 200 people whose main research areas are at the crossroads of two main axes:

- The identification of major health issues that can be addressed by Imaging.
- The identification of the major Health issues that can be addressed by Imaging. The identification of the theoretical locks in signal & image processing, modelling & digital simulation dedicated to the imaging of the living.
The main site of the laboratory is located on the Doua campus, Villeurbanne ( The post will be located on this site.

The candidate will be under the supervision of Frederic Cervenansky, head of the IT and development department, and integrated in this same department.

Duration: 6 months renewable twice.

Constraints and risks

Quality of life at work :
The candidate will benefit from the advantages made available by the CNRS regional delegation on the Doua campus:
- Extra-curricular assistance
- Catering, Transportation assistance
- Leave entitlement (from 45 days/year), teleworking under conditions
- Establishment involved (QWL disability, diversity, parity)
Mobility support
Dynamic Campus
- Sports and cultural facilities
- Exceptional working environment
- Campus map: soft transport

We talk about it on Twitter!