Senior Data Modeller

# Senior Data ModellerVNG
- Lake Towers, Évora, Fundão, Lisboa
- Expo, VNG
- Cais GaiaApply for this job
* Permanent
* Experienced Professionals
* Data & AI
* ID **-en\\_GB## YOUR ROLEYou will lead a modelling strategy for scientific data harmonization work.
This work aims to strengthen mechanistic understanding of disease and make integrated FAIR data products available to R&D scientists for rapid query and decision-making.
You turn ambiguous scientific requirements into clear canonical models, make and document ontology decisions, and set the standards for identifiers, provenance and schema governance across data assets.
* Lead modelling strategy across data harmonization, pipeline validation, knowledge graph and FAIR data product requirements
* Translate ambiguous scientific requirements into clear conceptual, logical and canonical data models
* Model biomedical entities and relationships including genes, targets, diseases, indications, phenotypes, mechanisms, biomarkers, tissues, cell types, assay modalities, evidence, provenance and causal relationships
* Make ontology reuse, extension and mapping decisions, with documented rationale
* Define persistent identifiers and consistent provenance fields across data assets
* Drive schema review, approval, versioning and publication processes in GitHub, including changelogs, tagged releases and downstream impact assessment
* Define validation rules and data quality checks for ontology terms, ranges, required fields, ID and label consistency, cross-field consistency and provenance completeness
* Identify modelling risks early: metadata gaps, ontology conflicts, source data quality issues, lineage gaps and downstream compatibility problems
* Design modular, reusable and future-proof models aligned to FAIR principles and enterprise standards
* Work with scientific knowledge engineering, biology SMEs, data engineering, knowledge graph engineering, product management, data stewards and platform teams
* Mentor junior and mid-level modelers##

YOUR PROFILE
* MSc or PhD (or equivalent professional experience) in biology, biomedical sciences, bioengineering, genetics, neuroscience, bioinformatics, computational biology or a related field
* More than 6 years of experience in scientific or biomedical data modelling, data harmonization or knowledge engineering, with senior ownership
* Strong conceptual, logical and canonical modelling experience for complex biomedical or scientific domains
* Practical, in-depth experience with LinkML or an equivalent schema framework: classes, slots, ranges, identifiers, required fields, constraints, cardinality, descriptions and ontology bindings
* Strong data harmonization

experience:
source-to-canonical mapping, controlled vocabulary alignment, persistent identifiers, lineage and provenance
* Proven experience defining validation rules and data quality checks: ontology term validity, ranges, required fields, ID and label consistency, cross-field consistency and provenance completeness
* Strong understanding of FAIR principles, metadata standards, provenance and schema versioning
* Strong command of biomedical ontologies and vocabularies such as HGNC, Ensembl, UniProt, MONDO, Disease Ontology, HPO, EFO, UBERON, Cell Ontology, Gene Ontology, Reactome, KEGG, ChEBI, OBI, LOINC, UCUM, ECO, SEPIO, Relation Ontology and PATO
* Experience managing the schema lifecycle with GitHub-based repositories, semantic versioning, changelogs, data dictionaries and metadata catalogues
* Experience designing models that support pipelines, APIs, knowledge graphs, FAIR data products and analytical workflows
* Solid Python and a working command of SQL, used for validation, mapping checks and exploration of real biomedical datasets
* A public or shareable repository (GitHub, GitLab or similar) demonstrating schema and governance work.
Please include the link in your application
* Excellent stakeholder management and communication;
* Fluent EnglishPreferred qualifications
* Semantic modelling technologies: RDF, OWL, JSON-LD, SHACL, ShEx and SPARQL; knowledge graph modelling
* Schema or model registry, data catalogue and metadata registry tooling
* Lineage and provenance modelling, and FAIR metadata assessment
* Query-based validation using SQL or Python and notebooks for model conformance, ontology mapping or data quality checks
* Agentic AI or LLM-assisted mapping and curation, with robust validation
* Experience in pharmaceutical R&D or another regulated research environment
* Cloud platforms, Docker and workflow orchestration
* Applied machine learning and/or broad data science
* Experience mentoring or leading a small technical team
* Scientific curiosity paired with engineering discipline
* Critical thinking and attention to data provenance and quality
* Comfort with ambiguity, and the ability to move between scientific meaning and technical implementation
* An impact-driven mindset in a fast-paced environment
* Portuguese fluency## WHAT YOU ́LL LOVE ABOUT WORKING HERE
* Join