About this role
Who we are ?
We are Pierre Fabre Laboratories, a global leader combining pharmaceutical expertise with dermo-cosmetics to support consumers and patients at every stage of their care journey.
Our portfolio includes several medical franchises and international brands such as Eau Thermale Avène, Ducray, A-Derma, Klorane, René Furterer, and Pierre Fabre Oral Care.
By joining us, you become part of a meaningful company where the human dimension is essential. You become a participant in the "We Care Movement," a movement that values excellence and innovation within passionate teams. Together, we push the boundaries of science to unite health and beauty for the benefit of all, because Every time we care for a single person, we make the whole world better.
Present in 120 countries with a team of over 10,000 employees, we are proud to create a scientific and human impact, today and tomorrow! If caring is at the heart of your values, join Pierre Fabre Laboratories and become a key player in the “We Care Movement".
Your mission
Votre rôle au sein d’une entreprise pionnière en pleine expansion.
L’objectif de ce stage est de concevoir et de développer un outil interne de classification de l’oncogénicité afin de soutenir ce processus. Cet outil comprendra :
- Une API destinée à être intégrée aux pipelines existants de l’équipe Data Science.
- Une application dédiée permettant aux collaborateurs R&D d’interroger directement les variants.
Le développement de cette solution en interne permettra à l’équipe de disposer d’une alternative fiable et pérenne aux outils sous licence externe, tout en établissant une base technologique évolutive qui pourra continuer à être enrichie après le stage.
Dans le cadre de ce stage, vos missions seront :
1. Collecter et préparer des données
- Constitution et curation des données d’entraînement à partir de sources publiques (COSMIC, cBioPortal/TCGA/ICGC, ClinVar).
- Mise en place du pipeline d’annotation des variants.
2. Développer le modèle de machine learning
- Conception du modèle de classification de l’oncogénicité.
- Validation des performances et comparaison avec les approches existantes (benchmarking).
3. Développer l’application et les interfaces
- Mise à disposition du modèle via une API interne pour les équipes Data Science.
- Développement d’une application front-end à destination des équipes R&D.
- Rédaction de la documentation et transfert des connaissances.
Les plus du stage :
- Missions diversifiées
- Gratification attractive
- Possibilité de réaliser un jour de télétravail par semaine après un mois d'intégration
- Dotations produits
- Restaurant d'Entreprise ou Titres Restaurants
Le stage se déroulera sur notre site de Langlade, à Toulouse (31) , pour une durée de 6 mois , à partir de janvier 2027.
Merci d’indiquer vos dates de disponibilités dans votre CV.
Young People
___________________________________________________________________________
Your role within a pioneering, rapidly expanding company.
The objective of this internship is to design and develop an internal oncogenicity classification tool to support this process. The solution will include:
- An API designed to be integrated into the Data Science team's existing pipelines.
- A dedicated application enabling R&D colleagues to query genetic variants directly.
By developing this solution in-house, the team will gain a reliable and sustainable alternative to externally licensed tools, while establishing a scalable technological foundation that can continue to evolve beyond the internship.
During this internship, your main responsibilities will be:
1. Data Collection & Preparation
- Curate and prepare training datasets from public sources (COSMIC, cBioPortal/TCGA/ICGC, ClinVar).
- Develop and implement the variant annotation pipeline.
2. Machine Learning Model Development
- Design and develop the oncogenicity classification model.
- Validate model performance and benchmark it against existing approaches.
3. Application & Interface Development
- Deploy the model through an internal API for the Data Science teams.
- Develop a front-end application for R&D users.
- Prepare documentation and ensure effective knowledge transfer.
Benefits :
- Diverse and challenging assignments
- Attractive internship compensation
- Opportunity to work remotely one day per week after the first month of onboarding
- Employee product allocation
- Access to the company restaurant or meal vouchers
The internship will take place at our Langlade site in Toulouse, France , for a 6-month period , starting in January 2027 .
Please indicate your availability dates in your CV.
#
Who you are ?
#
Vos compétences au service de projets novateurs.
Vous êtes étudiant(e) en dernière année de Master (Bac+5) ou en école d’ingénieurs, spécialisé(e) en bioinformatique, biologie computationnelle, biostatistiques ou dans un domaine équivalent, et recherchez un stage de fin d’études de 6 mois en environnement industriel.
Compétences requises :
- Maîtrise de Python ou R (une expertise dans l’un des deux langages est indispensable ; une connaissance de l’autre est appréciée).
- Solides connaissances en génomique du cancer et en interprétation des variants somatiques.
- Intérêt pour les méthodes de machine learning appliquées à la biologie (XGBoost, Random Forest et autres modèles de classification).
- Capacité à développer une application ou une interface web simple permettant de rendre les résultats accessibles à des utilisateurs non techniques (Shiny, Streamlit, Dash, etc.).
- Rigueur méthodologique, autonomie et sens de la documentation.
Serait un plus :
- Expérience avec des outils d’annotation de variants (VEP ou équivalent).
- Développement d’API REST.
- Conception d’applications internes de valorisation et d’exploitation des données.
____________________________________________________________________________
Put your skills to work on innovative projects.
You are currently in the final year of a Master’s degree (MSc, equivalent to a 5-year higher education degree) or an engineering school program, specializing in bioinformatics, computational biology, biostatistics, or a related field, and are looking for a 6-month end-of-studies internship in an industrial environment.
- Proficiency in Python or R (strong expertise in one language is required; familiarity with the other is a plus).
- Solid knowledge of cancer genomics and somatic variant interpretation .
- Interest in machine learning applied to biology , including approaches such as XGBoost, Random Forest , and other classification models.
- Ability to develop a simple web application or user interface to make results accessible to non-technical users (e.g., Shiny, Streamlit, Dash ).
- Strong methodological rigor, autonomy, and attention to documentation.
Nice to Have
- Experience with variant annotation tools (e.g., VEP or equivalent).
- Experience developing REST APIs .
- Experience designing and developing internal data applications for data analysis and visualization.
At Pierre Fabre Laboratories, we believe that our greatest asset is our people.
We are committed to a policy of Equal Employment Opportunity and will not discriminate against an applicant or employee based on race, color, religion, creed, national origin or ancestry, sex, sexual orientation, gender identity or expression, age, physical or mental disability, veteran or military status, genetic information, or any other legally recognized protected basis under federal, state, or local law. The information collected by this application is solely to determine suitability for employment, verify identify, and maintain employment statistics on applicants. Applicants with disabilities may be entitled to reasonable accommodation under the Americans with Disabilities Act and certain state or local laws. Please inform the company’s personnel representative if you need assistance completing this application or to otherwise participate in the application process. Thus, we commit to considering all applications equally, without fail.