Principal Data Scientist

Position Summary Lead the design, implementation, and evolution of scientific data products and integration strategies supporting AI-enabled drug discovery and development. Create scalable, interoperable, AI-ready data products connecting discovery, preclinical, clinical, safety, and real-world evidence; enable validated-biomarker data assets. Establish data architecture, integration strategy, metadata framework, and productization approach for semantic reasoning, knowledge graphs, GraphRAG, advanced analytics, and agentic AI. Define the future-state scientific data ecosystem with stakeholders and ensure high-quality products for translational science and patient safety. Key Responsibilities Define and execute a scientific data product strategy for discovery research, translational science, preclinical safety, clinical development, pharmacovigilance, and real-world evidence. Design integration frameworks and data harmonization across SEND, SDTM, ADaM, MedDRA, imaging, omics, biomarker, pathology, and real-world data. Lead AWS-based digital platform implementation strategy; partner to deliver pipelines/data products. Develop curated datasets, semantic-ready data products, feature stores, metadata products, scientific data services, and AI-ready data assets. Define metadata standards and data quality; implement lineage/provenance/traceability and FAIR; establish monitoring controls. Build predictive AIML models for translational safety decision making. Required Qualifications Master’s or PhD in CS, Data Engineering, Bioinformatics, Biomedical Informatics, Information Systems, Computational Biology, or related. 5+ years in scientific data engineering/architecture/products/life sciences informatics. Experience delivering enterprise-scale scientific data products; supporting drug discovery/development/clinical research/pharmacovigilance. Experience developing predictive models in relevant areas. Technical Expertise Data architecture/modeling, data product design, cloud-native platforms, metadata management, data governance, predictive model development. AWS-based platforms; data lakes/lakehouses; distributed processing; APIs/data services; data cataloging/lineage. Familiarity with SEND, SDTM, ADaM, MedDRA. Preferred Qualifications Knowledge graphs/semantic architectures/GraphRAG; AI-ready data products & feature stores; ontology-driven integration; partnering with cloud/platform teams; regulated environments. Familiarity with FHIR, OMOP, DICOM; biomarker/omics standards. Benefits (explicitly listed) Vacation: 120 hours/year; Sick time: 40 hours/year (CO: 48; WA: 56); Holiday pay (incl. Floating Holidays): 13 days/year; Work/Personal/Family Time: up to 40 hours/year; Parental Leave: 480 hours; Bereavement: 240 hours (immediate) / 40 hours (extended); Caregiver Leave: 80 hours (52-week rolling period); Volunteer Leave: 32 hours/year; Military Spouse Time-Off: 80 hours/year. #J-18808-Ljbffr