STAGE Machine Learning

Date de mise à jour de l’offre

DREEM SAS :

Dreem est une entreprise de santé digitale spécialisée dans la médecine du sommeil. Avec plus de quarante brevets exclusifs et une très large base de données, Dreem est une entreprise leader dans le diagnostic, les soins et la recherche sur le sommeil. Dreem possède un réseau unique de 350+ partenaires universitaires et de chercheurs - dont Harvard Medical School, Stanford School of Medicine, l'université de Cambridge ou encore l'université d'Oxford.

Description de la mission

In order to better help our users, Dreem seeks to screen people with a high risk of sleep apnea to then diagnose and treat their sleep apnea. You will work on an innovative project: detecting accurately sleep breathing disturbances with the microphone of a smartphone. You will work on all aspects of ML, from data gathering to model training and optimization for deployment on smartphones. Your work will potentially impact the lives of thousands.

1) Define and run a data acquisition protocol: In order to collect data on various devices and a variety of subjects you will work with our specialists to define a robust data acquisition protocol that will ensure that your model will perform well in the wild.

2) Build lightweight and efficient models using public and internal datasets: while your data collection protocol will run, you will experiment with several types of Machine Learning and Deep Learning architecture on public and internal datasets.

3) Optimize your architecture for deployment on smartphones: As the end goal is to deploy the model on a smartphone, you will collaborate with our mobile developers to ensure that the model can run smoothly and efficiently on a phone.

4) Evaluate and finetune your model on the data you collected: Once your data acquisition protocol will be finished you will be able to finetune the model you designed on these data in order to evaluate the performances in a real-life setting

Profil recherché

We are looking for someone:

1) Interested in the project and shaping the future of sleep care with technology Studying towards a MSc/PhD in Computer Science, Machine learning or a quantitative field

2) With strong skills in Machine Learning/Deep Learning proven via personal projects, classes, or previous experiences With good knowledge of Python and of a Deep Learning framework (Keras, Torch, Tensorflow)

3) With Knowledge or strong interest in signal processing (spectral analysis, filtering, …),
previous experiences/projects with sound are a plus With Organizational skills and a pragmatic mindset, previous experiences building datasets are a bonus

4) Fluent in English

Niveau de qualification requis

Bac + 4/5 et +
  • Employeur
    DREEM SAS
  • Secteur d’activité de la structure
    Santé - Social - Citoyenneté - Sécurité
  • Effectif de la structure
    De 21 à 50 salariés
  • Site internet de la structure
    http://dreem.com
  • Type de stage ou contrat
    Stage pour lycéens et étudiants en formation initiale
  • Date prévisionnelle de démarrage
  • Durée du stage ou contrat
    Plus de 4 mois et jusqu'à 6 mois
  • Le stage est-il rémunéré ?
    Oui
  • Niveau de qualification requis

    Bac + 4/5 et +
  • Lieu du stage
    86 rue Notre Dame de Nazareth
    75003 PARIS 3E ARRONDISSEMENT
  • Accès et transports
    Métro Strasbourg Saint Denis