Senior data scientist – multi‑omics ai & target identification - cdi

Qui sommes-nous ?

Pierre Fabre est le 2ème laboratoire dermo-cosmétique mondial, le 2ème groupe pharmaceutique privé français et le leader des produits vendus hors prescription dans les pharmacies en France.

Son portefeuille compte plusieurs franchises médicales et marques internationales dont Pierre Fabre Oncologie, Pierre Fabre Dermatologie, Eau Thermale Avène, Klorane, Ducray, René Furterer, A-Derma, Naturactive et Pierre Fabre Oral Care.

Implanté depuis toujours en région Occitanie, fabricant plus de 95% de ses produits en France, le groupe emploie près de 10 000 collaborateurs dans le monde et distribue ses produits dans quelque 130 pays. Pierre Fabre est détenu à 86% par la Fondation Pierre Fabre, une fondation reconnue d’utilité publique, et secondairement par ses collaborateurs à travers un plan d’actionnariat salarié.

En 2021, Ecocert Environnement a évalué la démarche de responsabilité sociétale et environnementale du Groupe selon la norme ISO 26000 du développement durable et lui a attribué le niveau « Excellence ».

Pierre Fabre est reconnu comme l’un des « Meilleurs Employeurs du Monde 2021 » par Forbes. Notre groupe est classé dans le Top 6 de l’industrie cosmétique et dans le Top 7 de l’industrie pharmaceutique dans le monde. Nous sommes convaincus que notre engagement et notre passion font préserver notre indépendance et vivre notre raison d'être.


Votre mission

We are seeking in Toulouse (Oncopole- Langlade Location) a talented and highly motivated Senior Data Scientist - Multi‑Omics AI & Target Identification with strong expertise in multi‑omics analysis, machine learning, and AI for biological data to accelerate target identification, translational research, and precision medicine strategies.

As a key member of the Data Science & Biometry Department within Pierre Fabre R&D Medical Care, you will design and develop AI systems capable of learning from high‑dimensional biological data (genomics, transcriptomics, proteomics, functional screens) to deepen disease understanding, uncover pathway‑level mechanisms, and reveal cancer vulnerabilities across indications.

This role sits at the interface of AI research, computational biology, and drug discovery, and is embedded within the Methods & Innovation team, responsible for cross‑functional initiatives involving advanced AI methodologies.

Your role within a pioneering company in full expansion:

Key Responsibilities

* Develop and apply machine learning and deep learning models to integrate multi‑omics data for target identification and prioritization.
* Contribute to biological and disease understanding by identifying molecular mechanisms, pathways, and vulnerabilities across cancer indications.
* Support diverse downstream assessments, including target discovery, toxicity prediction, and patient stratification.
* Design and train advanced models leveraging representation learning, self‑supervised learning, and domain adaptation.
* Apply and adapt transformer‑based architectures to biological and omics data.
* Ensure strong standards for model robustness, reproducibility, interpretability, and scientific validity.
* Work with HPC and/or cloud environments to scale model training and experimentation.
* Collaborate closely with biologists, translational scientists, and drug discovery teams to translate biological questions and hypotheses into AI‑driven solutions.
* Contribute to shared AI frameworks and reusable methodological components across R&D.

This position is compatible with teleworking up to 2 days a week according to company rules.

We offer an attractive remuneration/benefits package: Incentives, profit-sharing, Pierre Fabre shareholding with matching contribution, health and provident insurance, 16 days of holidays (RTT) in addition to 25 days of personal holidays, public transport participation.


Qui êtes-vous ?

Your skills at the service of innovative projects:

Education

* PhD or Master’s degree in Data Science, Computational Biology, or a related field.

Experience

* 5+ years of experience in data science applied to life sciences.
* Demonstrated experience in multi‑omics data analysis for target discovery or translational research.
* Hands‑on experience developing machine learning and deep learning models.

Technical Skills

* Strong proficiency in Python.
* Experience with deep learning frameworks (e.g., PyTorch).
* Solid knowledge of modern ML approaches, including transformers, representation learning, self‑supervised learning, and domain adaptation.
* Familiarity with HPC and/or cloud computing environments.
* Strong grounding in bioinformatics, cancer biology, and pathway-level reasoning.

Soft Skills & Mindset

* Strong analytical and structured thinking.
* Ability to translate biological, scientific, and strategic challenges into effective AI solutions.
* Excellent cross‑functional collaboration skills.
* High intellectual curiosity and innovation mindset.
* Professional proficiency in English (written and oral).

Nous sommes convaincus que la diversité est une source d’épanouissement, d’équilibre social et de complémentarité pour nos collaborateurs, nos offres sont donc ouvertes à toutes et tous sans restriction.