Biomedical Data Scientist — Knowledge Graphs & FAIR Data

Capgemini Engineering

Lisboa

Híbrido

EUR 55 000 - 75 000

Tempo integral

14 dias+

Recebe mais respostas dos empregadores

Envia um currículo específico para a oferta em poucos minutos.

Vantagens oferecidas por esta oferta de emprego

Hybrid work

Health and life insurance

Training and certifications programs

Career growth programs

Referral program with bonuses

Resumo da oferta

Capgemini Engineering in Portugal is seeking a Mid‑Senior Data Scientist with a biomedical focus to design and govern data foundations for life sciences projects. You will bridge science, engineering, and product teams to deliver scalable, FAIR data solutions and robust ML-enabled insights.

You'll build schema‑driven pipelines in Python/SQL, drive knowledge graph development with RDF/OWL/SPARQL, and apply Gen AI tools to extract value from complex biomedical data, while upholding data governance

Qualificações

MSc or PhD in Bioinformatics, Biomedical Engineering, Molecular/Cell Biology, Neuroscience, Genetics, or related field.
Excellent stakeholder management — able to drive alignment across scientific, engineering, and product stakeholders.
Data modelling and harmonization experience across complex biomedical domains including source-to-canonical mapping, ontology alignment, persistent identifiers, and provenance.
Strong Python and SQL skills; comfortable building data pipelines and performing exploratory data analysis.
Applied data science / ML experience relevant to knowledge graph or scientific data work.
Strong communication skills with both technical and business stakeholders.
Critical thinking, intellectual curiosity, and impact‑driven mindset.
Ability to adapt and manage priorities in fast‑paced environments.
Fluent in Portuguese and English.

Responsabilidades

Designing and governing biomedical data models: leading source-to-canonical mapping, ontology alignment, and schema governance including versioning, changelogs, and downstream impact assessments to ensure data integrity and scientific accuracy across complex biomedical domains
Building and maintaining data pipelines: developing robust, schema-driven pipelines in Python and SQL, performing exploratory data analysis, and implementing validation frameworks that support high-quality, reproducible scientific workflows
Driving knowledge graph development: applying hands‑on experience with RDF, OWL, SPARQL, and property graph modelling tools such as Neo4j and GraphDB to build and enrich knowledge graphs that connect biomedical entities across diverse data sources
Applying machine learning and Gen AI: leveraging applied ML experience and familiarity with Gen AI tools (including text generation APIs, chatbots, and enterprise search solutions) to extract insight and value from scientific data at scale
Championing FAIR data principles: designing and delivering FAIR data products, leading harmonisation efforts across multiple source systems, and ensuring persistent identifiers and provenance are embedded into every data product
Aligning stakeholders across disciplines: driving alignment between scientific, engineering, and product teams through clear communication, structured documentation, and a solutions‑focused mindset that keeps complex projects moving forward
Working with biomedical ontologies and controlled vocabularies: applying deep knowledge of resources such as Ensembl, UniProt, and Gene Ontology, including judgement on when and how to extend or map them to real‑world data challenges