Senior Clinical Data Scientist

Karius•Redwood City, CA

1d•Remote

About The Position

The Sr. Clinical Data Scientist will serve as the primary data architect for Karius’s large-scale commercial real-world evidence registry. This role sits at the intersection of clinical research and health informatics, responsible for designing and operationalizing EHR data extraction pipelines across participating health systems, translating clinical research requirements into structured data specifications, and transforming heterogeneous real-world data into analysis-ready datasets that support biostatistics and clinical development. The ideal candidate is equally comfortable negotiating data specifications with a site’s Epic Clarity team and working alongside biostatisticians to structure complex longitudinal datasets.

Requirements

Bachelor’s degree in Health Informatics, Biomedical Informatics, Data Science, Computer Science, Biostatistics, Epidemiology, Public Health, or a related quantitative or clinical field with 5-6+ years of relevant experience; a master’s degree or MPH with 3-4+ years of relevant experience; or a Ph.D. with 1-2+ years of relevant experience.
Minimum 4+ years of hands-on experience with Epic Clarity and/or other systems; ability to write and optimize SQL queries against large clinical data warehouses.
Demonstrated experience designing or executing EHR data extractions for research or registry studies, including direct engagement with health system informatics or IT teams.
Proficiency in Python and/or R for data transformation, cleaning, and quality assessment at scale.
Familiarity with real-world data standards including OMOP CDM, CDISC, HL7 FHIR, SNOMED CT, ICD-10, and LOINC.
Experience supporting biostatistics or data science teams with dataset preparation, variable derivation, and analysis-ready data delivery.
Ability to communicate technical data concepts clearly to non-technical clinical site staff, research coordinators, and clinical operations colleagues.
Strong technical aptitude, including the ability to write and interpret complex SQL queries.
Ability to translate technical clinical data requirements into clear, practical guidance for non-technical stakeholders.
Strong attention to detail and comfort working with complex data sharing specifications.
Intellectual curiosity and sound judgment when evaluating clinical data, workflows, and downstream implications.
Ability to move fluidly between hands-on technical work and stakeholder-facing communication.
Collaborative communication style, with the ability to partner effectively with site coordinators, clinical teams, and cross-functional stakeholders.

Nice To Haves

Experience with large, multi-site, longitudinal real-world datasets strongly preferred.
Knowledge of clinical trial data management principles and ICH-GCP a plus.

Responsibilities

Own EHR data extraction specifications for the AXIS registry, including data element definitions, data dictionaries, field mappings, and site-specific translation logic across heterogeneous EHR environments.
Serve as the primary technical liaison to site informatics and IT teams, translating clinical research data requirements into executable data queries and extraction protocols; primary experience with Epic Clarity and/or Caboodle required.
Design and validate data extraction pipelines that ingest structured EHR data (diagnoses, medications, labs, procedures, utilization) from multiple health systems into a harmonized, analysis-ready format.
Perform data quality assessment, anomaly detection, and cross-site consistency validation; implement processes to identify and resolve data integrity issues with sites.
Partner closely with the biostatistics team to deliver clean, structured, well-documented datasets; support data preparation, variable derivation, and dataset specifications for statistical analysis plans.
Collaborate with clinical operations on site onboarding for clinical site data integration, including support for data governance agreements, BAAs, and technical feasibility assessments.
Build and maintain the registry data model, data lineage documentation, and codebook to ensure reproducibility and audit-readiness.
Apply working knowledge of real-world data standards (OMOP CDM, HL7 FHIR, SNOMED, ICD-10, LOINC) to support data harmonization across sites with diverse EHR configurations.
Support seamless integration between EHR data, the registry EDC, and Karius' standardized internal clinical database.
Support broader clinical research data analytics across programs, including integrating datasets from multiple sources, building analysis-ready analytic files, and data visualization to support clinical development and biostatistics teams
Contribute to the design of data collection strategies for future real-world evidence studies and registry expansions.