Data Scientist H/F Servier

Data Scientist

Role Expectations:

The DSDM unit at Servier is at the forefront of data-driven drug discovery. We are seeking a Senior Data Scientist (PhD level) with expertise in knowledge graphs, artificial intelligence, and large-scale biological and chemical databases. You will lead the development of advanced data integration and AI models, transforming how we connect, interpret, and leverage high-dimensional data to accelerate therapeutic innovation.

Main Responsibilites:

- Design, develop, and deploy knowledge graph architectures integrating heterogeneous data from biological, chemical, and clinical domains.
- Lead AI/ML projects for entity resolution, relationship extraction, and property prediction in drug discovery pipelines.
- Architect scalable data ingestion pipelines for high-throughput bioactivity data, omics datasets, and compound libraries.
- Build interactive tools for scientists using Python-based frameworks (e.g., FastAPI, Dash, Streamlit) to explore large, interconnected datasets.
- Apply dimensionality reduction and clustering techniques on high-dimensional data (e.g., transcriptomics, chemical descriptors).
- Collaborate with cheminformatics, bioinformatics, and medicinal chemistry teams to generate actionable insights.

Required Skills and Experience:

Educational & Professional Background

- PhD in Computer Science, Bioinformatics, Cheminformatics, Computational Biology, or related fields
- 5+ years of experience (including PhD/postdoc) working on data-centric problems in life sciences or healthcare
- Proven ability to design and implement production-grade knowledge graphs integrating complex biological and chemical data

- Demonstrated track record of delivering AI/ML models in drug discovery or biomedical research
- Fluent english

Hard Skills

Programming Languages:

- Expert-level Python (including libraries such as pandas, NumPy, scikit-learn, PyTorch/TensorFlow for ML)
- Good command of SQL for complex queries on large relational databases
- Experience with Neo4J-Cypher for semantic queries on knowledge graphs

Knowledge Graphs & Ontologies:

- Hands-on with Neo4j, GraphDB
- Proficient in RDF, OWL and graph modeling best practices
- Familiarity with biomedical ontologies (e.g., MeSH, ChEBI, GO)

Databases & Big Data:

- Experience with biological/chemical databases (e.g., ChEMBL, PubChem, UniProt, PDB, Ensembl)
- Exposure to NoSQL solutions (e.g., MongoDB) for flexible data modeling

AI & ML:

- Proficiency in supervised and unsupervised learning methods

Soft Skills

- Demonstrated ability to work collaboratively in multidisciplinary teams and communicate complex scientific concepts effectively.
- Strong ability to work in a team is mandatory
- Pragmatic and result oriented
- Ability to work on multiple projects in parallel respecting deadlines
- Strong independence, strong organization skills
- Innovative and curious mind

Nous sommes engagés pour l'égalité des chances et le développement des talents dans toute leur diversité. Nous accordons autant de valeur à l'expérience qu'à l'envie de s'engager au quotidien pour être utile au progrès thérapeutique au bénéfice des patients. Si vous vous reconnaissez dans cette offre et ces quelques lignes, saisissez cette opportunité de nous rencontrer.