Principal Data Scientist - Oncology

Role: Principal Data Scientist - Oncology within Johnson & Johnson's Data Science and Digital Health team, focusing on developing a scalable knowledge graph infrastructure for oncology R&D data. Responsibilities: design and implement semantic data models, curate ontologies, develop ingestion pipelines, and enable AI/ML applications through graph-based data integration; collaborate with cross-functional teams including clinical and discovery scientists, IT, and DevOps; deploy and maintain high-availability graph systems; document data flow and provenance. Requirements: Ph.D. or Master's in bioinformatics, computer science, or related fields; 5+ years in health informatics or biomedical data science; proven experience with large-scale knowledge graphs, ontologies, RDF/OWL, SPARQL, and biomedical datasets; programming expertise in semantic web technologies, graph databases (Neo4j, Neptune), and data modeling; familiarity with clinical, genomics, or proteomics data; experience with CI/CD, containerization, and stakeholder management. Preferred: background in semantic technologies for biomedical applications, experience in pharma or healthcare domains, and knowledge of NLP, RAG, and predictive modeling. HighValue: oncology R&D data, knowledge graphs, semantic web standards, biomedical ontologies, data integration, and interoperability. Location: Spring House PA (preferred), Cambridge MA, San Diego CA, or Titusville/Raritan NJ; no remote option; <15% travel.