Bioinformatics Specialist

Company Description

Eno Health is an AI-powered platform designed to be the ultimate decision-support system for healthcare providers seeking to facilitate personalised care and long-term wellness for patients. We are building a compliant, secure, and European-sovereign biomedical AI solution for personalised healthcare. The platform streamlines practitioners' workflows and patient data processing, enabling faster, more precise clinical decisions.

Role Description

You will own the biological content layer of our knowledge graph: the pathways, genes, molecules, and mappings that connect them. Where our data scientists own the models and evaluation methodology, you own the biology being reasoned over; its correctness, its provenance, and its computability. The problems are integrating curated pathway and genomic knowledge into a property graph at clinical quality, building the molecular identity layer that makes supplements and medications computable, and turning pharmacogenomic and polygenic evidence into structured artefacts a clinician can sign off. This is a curation/engineering role, not a wet-lab or pure research role. Everything you produce is versioned, provenance-tracked, and gated by clinical review before it enters production.

Qualifications

• A strong foundation in molecular biology, genetics, or pharmacology (important: critically evaluate pathway annotations, gene–drug evidence, and published associations, not merely ingest them).
• Hands-on experience with the major biomedical knowledge resources: pathway databases (Reactome, WikiPathways, or KEGG), gene and variant resources (ClinVar, PharmGKB/ClinPGx, PGS Catalog), and chemical entity databases (ChEBI, PubChem, DrugBank or equivalents).
• Ontology and terminology engineering: practical experience with OBO-family ontologies (Mondo, HPO, ChEBI, GO), identifier mapping and cross-referencing, and the judgement to handle the cases where mappings are lossy or contested.
• Genomic data competence: VCF processing, variant annotation, and pharmacogenomic star-allele logic. You do not need to have built a clinical-grade calling pipeline, but you need to understand why diplotype assignment is harder than it looks.
• Strong Python for data pipelines: reproducible, tested, versioned. Experience with graph data structures or graph databases is a strong advantage.
• The documentation discipline of a regulated environment. Curation at ENO feeds a medical-device technical file; provenance, reproducibility and named-reviewer sign-off are requirements of the job, not aspirations.
• MSc or PhD in bioinformatics, computational biology, genetics, or a related field, or equivalent practical experience.
• Property graph or semantic-web experience: Neo4j, RDF/OWL, SPARQL, or the Biolink Model for edge semantics and provenance.
• Cheminformatics beyond identifiers: structure normalisation, salt/ester/parent-compound resolution, RDKit.
• FHIR Genomics or clinical interoperability standards.
• Experience with national medication registries or supplement regulatory data in the Benelux market.
• Nutrigenomics, systems medicine, or functional medicine literacy (our clinical domain reasons across nutrition, lifestyle, and conventional pharmacotherapy).
• Experience using LLMs as curation accelerators (extraction, mapping suggestion, literature triage) while keeping a human reviewer in the loop.

What We Offer

• Ownership of the biological substance of a clinical AI platform at the stage where the schema is still yours to shape.
• Competitive salary and an equity package.
• Hybrid working from our Ghent base, with flexibility for remote work.
• Direct collaboration with the founding team and clinical leadership.