Principal Scientist, Data Science (Translational Knowledge Engineering)
About the role
The Principal Translational Knowledge Architect & Graph Lead will be responsible for designing and implementing the semantic and knowledge architecture that enables AI-driven reasoning across the drug discovery and development lifecycle.
Responsibilities
Design and maintain enterprise knowledge models spanning: Discovery biology, Toxicology, Safety pharmacology, Pathology, Clinical development, Pharmacovigilance, Real-world evidence.
Create semantic frameworks that support translational reasoning across the R&D lifecycle.
Lead ontology strategy, development, governance, and lifecycle management.
Curate and extend biomedical ontologies supporting translational safety and efficacy use cases.
Establish ontology governance processes, quality standards, and semantic review procedures.
Ensure semantic consistency, provenance, traceability, and FAIR data principles.
Design RDF-based knowledge graph architectures and related semantic technologies.
Develop semantic mappings, inference rules, and reasoning frameworks supporting scientific decision-making.
Define knowledge representations enabling GraphRAG, semantic retrieval, AI agents, and reasoning systems.
Establish semantic interoperability across heterogeneous data sources and standards.
Develop semantic bridges across major industry standards and ontologies, including: SENDS, DTM, ADM, DRA, HPOM, ONDO, FHIR, HIROMO, Cell Ontology, Protein Ontology.
Partner with stakeholders across Discovery, Preclinical Safety, Clinical Development, Pharmacovigilance, Data Science, and Digital Health.
Collaborate with engineering teams responsible for data products, pipelines, and AI platforms.
Influence enterprise semantic strategy and represent the organization in external standards and ontology communities when appropriate.
Requirements
Education: PhD or Master’s degree in Biomedical Informatics, Bioinformatics, Computational Biology, Computer Science, Information Science, Knowledge Engineering, or related scientific discipline.
Experience: 5+ years of experience in biomedical informatics, semantic technologies, knowledge engineering, or scientific data architecture.
Technical Expertise: Deep expertise in ontology development and governance, knowledge representation, RDF, OWL, SHACL, SPARQL, semantic web technologies, enterprise ontology management platforms, RDF graph architectures, semantic APIs, FAIR data principles.
Domain Knowledge: Strong familiarity with one or more of translational science, toxicology, safety pharmacology, clinical development, pharmacovigilance, regulatory data standards.
Preferred Qualifications: Experience building semantic foundations for AI, GraphRAG, agentic AI, or scientific reasoning systems, familiarity with LLM-based retrieval and reasoning architectures, experience supporting translational safety, efficacy, biomarker, or mechanistic reasoning use cases, contributions to ontology standards, open-source biomedical ontologies, or scientific knowledge graph initiatives.
Qualifications
Strategic thinker capable of translating scientific challenges into scalable knowledge architectures.
Strong communicator who can engage effectively with scientists, clinicians, data scientists, engineers, and senior leadership.
Ability to operate in ambiguous, highly cross-functional environments.
Passion for advancing AI-enabled drug discovery and development through semantic and knowledge-driven approaches.