Senior Clinical AI Scientist - Causal Graph & LLM

Eno Health; Brussel; Hybride; EUR 90 000 - 130 000; Plein temps

Avantages offerts par ce poste

Hybrid work

Equity package

Résumé du poste

Eno Health is seeking a data-science lead to own the models, evaluation, and knowledge-graph rigour for its regulated clinical AI platform. This role focuses on causal reasoning over structured clinical data and validating models for medical-device audits.

Based in the Brussels metropolitan area with hybrid work flexibility, you will collaborate with clinical, engineering and product teams to turn clinical knowledge into computable artefacts and ensure reproducibility and sign-off by clinicians.

Qualifications

• Proficient in Python and PyTorch; self-hosted inference stack familiarity.
• Grounding in probabilistic graphical models and causal inference.
• Experience with graph databases (Neo4j) and graph-RAG approaches.
• Knowledge of biomedical ontologies (SNOMED CT, LOINC/UCUM, Mondo, HPO) and mapping to them.
• Applied statistics for model evaluation and reproducibility; GDPR Article 9 awareness.

Responsabilités

• Own the data-science layer of a regulated clinical AI system; models, evaluation, and knowledge graph.
• Collaborate with clinical, engineering, and product teams to turn clinical knowledge into computable artefacts.
• Document decisions with reproducibility and obtain clinician sign-off for inclusion in the knowledge graph.

Connaissances

Advanced Python

Causal inference

Bayesian networks

Federated learning

Formation

Master's or PhD in a quantitative field

Outils

PyTorch

Neo4j

Kafka

Flink

Description du poste

Eno Health is seeking a data-science lead to own the models, evaluation, and knowledge-graph rigour for its regulated clinical AI platform. This role focuses on causal reasoning over structured clinical data and validating models for medical-device audits.

Based in the Brussels metropolitan area with hybrid work flexibility, you will collaborate with clinical, engineering and product teams to turn clinical knowledge into computable artefacts and ensure reproducibility and sign-off by clinicians.