Data Science Internship

Sonio; Paris; On-site; EUR 10,000 - 13,000; Full time

Job summary

Sonio recherche un stagiaire DS/ML pour rejoindre l’équipe Data Science. Vous travaillerez à l’interface R&D, ML Engineering et produit, sous la supervision d’ingénieurs ML seniors, pour développer nos pipelines Deep Learning et Computer Vision.

Vous consoliderez votre compréhension clinique de l’échographie fœtale et explorerez des méthodes de détection/ segmentation, tout en vous intégrant à notre infrastructure ML (AWS, SageMaker, MLflow). Publication possible si les résultats le permettent.

Qualifications

• Master 2 / Bac+5 en école d'ingénieur ou université, spécialisation CS/DS, stage de 5–6 mois.
• Bonnes connaissances en ML/DL et volonté d'explorer les dernières méthodes.
• Solide Python et PyTorch/HuggingFace, et familiarité avec segmentation/detection.
• Intérêt fort pour vision par ordinateur et la santé des femmes.
• Anglais, et idéalement le français.

Responsibilities

• Développer la compréhension clinique de l’échographie fœtale dans les domaines anatomiques ciblés.
• Explorer et entraîner différentes approches pour la détection et la segmentation, et les intégrer dans l’infrastructure ML (AWS, SageMaker, MLflow).
• Explorer la possibilité de former des Foundation Models pour l’imagerie échographique.
• Réaliser des protocoles d’évaluation et documenter les expériences; publication possible si les résultats le permettent.

Skills

Machine learning

Deep learning

Computer vision

Python

PyTorch/HuggingFace

Segmentation/Detection

Anglais/Français

Education

Master 2 / Bac+5 en ingénierie ou DS

Tools

AWS

SageMaker

MLflow

Job description

About Sonio

Each year, 140M children are born. Birth defects affect 1 in 33 births in developed countries, and in 50% of cases, they are not detected during prenatal examinations. Prenatal medicine is particularly complex, and the scans impose heavy responsibilities on healthcare professionals. They can also be a source of stress for future parents.

Resulting from 5 years of collaboration between world-renowned experts from Necker Hospital and Ecole Polytechnique, Sonio uses artificial intelligence to improve prenatal screening and diagnosis. Based on patented algorithms and a proprietary expert database, Sonio aims to become the reference tool to help practitioners improve screening, reduce diagnostic errors, and optimize pregnant women’s medical path.

Sonio's mission is to improve women's and children's health by promoting access and quality of care through technological innovation, medical expertise, and collective intelligence.

About the role

We are looking for a DS/ML Engineer intern to join our Data Science team. Your mission will at the crossing of R&D, ML Engineering and product, supervised by senior ML engineers. You will work on developing of our existing Deep Learning/Computer Vision pipelines using State-of-the-art algorithms.

Your main mission will be to:

• Develop clinical understanding of fetal ultrasound in the anatomical areas you will work on
• Explore and train different approaches for Detection and Segmentation of anatomical structures and views, and integrate your results in our ML infrastructure (AWS, SageMaker, MLflow)
• Explore the possibility of training Foundation Models for Ultrasound Imaging
• Run evaluation protocols consistent with the way our models are evaluated during regulatory submissions, and document your experiments so the team can build on them. Publication is possible and encouraged if the results support it

About the profile

Sonio is a mission-driven company so interest in our mission is critical. Other requirements are:

• Currently in Master 2 / Bac+5 of Engineering School or University, you are majoring in Computer Science or Data Science and are looking for an internship lasting between 5 and 6 months
• Good knowledge of Machine Learning and Deep Learning algorithms, and the willingness to explore and work on state-of-the-art algorithms
• Solid Python and PyTorch/HuggingFace, and comfortable with segmentation and detection architectures
• Strong interest in computer vision and women’s health. A first experience with medical images is a plus
• You speak English and ideally French

We move fast and aspire to be transparent over the process - our objective is that the process from the first chat to an offer is no longer than a month. We also aspire to give an answer to every application in a week.