Harnham

Clinical Data Scientist

San Francisco, California, USA · full-time

Sponsorship not specifiedDetected 116 days ago

PythonGitPlatform EngineeringMachine LearningData ScienceNLPStatisticsComplianceHIPAAClinical TrialsClinical ResearchSASResearchCommunicationCollaboration

About the role

Job Description Clinical Data Scientist Hybrid or Remote Overview A growing organization in the healthcare and life sciences technology space is seeking a Clinical Data Scientist to support the final stages of its clinical data pipeline. This role focuses on transforming complex clinical datasets into clean, standardized, analysis ready deliverables for use
in clinical research and regulatory submissions. The ideal candidate is detail oriented, technically versatile, and passionate about delivering high quality clinical data. You will work closely with cross functional teams including Clinical Operations, Data Platform Engineering, and AI/ML teams to ensure accuracy, traceability, and compliance across all

Responsibilities

Build analysis ready datasets from diverse sources including EMRs, EDC systems, and internal abstraction tools.
Statistical Programming & Reporting Develop and generate Tables, Listings, and Figures (TLFs) for clinical study reports and interim analyses using SAS, R, or Python.
Data Integrity & Quality Control Perform comprehensive data cleaning and validation checks.
Cross Team Collaboration Partner with engineering teams to automate data cleaning and validation workflows.
Documentation Create and maintain clear documentation including data specifications, derivation logic, reviewers guides, and Define.xml to support audits and regulatory submissions.
Ad Hoc & Exploratory Analysis Support internal and external stakeholders with data queries, one off analyses, and insights that demonstrate the value of the platform.

Nice to have

This role focuses on transforming complex clinical datasets into clean, standardized, analysis ready deliverables for use in clinical research and regulatory submissions.
The ideal candidate is detail oriented, technically versatile, and passionate about delivering high quality clinical data.
You will work closely with cross functional teams including Clinical Operations, Data Platform Engineering, and AI/ML teams to ensure accuracy, traceability, and compliance across all data outputs.
candidates in the SF Bay Area are preferred but not required.
Data Transformation & Delivery Convert raw, manually abstracted, and AI processed clinical data into standardized formats (e.g., CDISC SDTM/ADaM) or client specific data models.
Investigate discrepancies to distinguish between true clinical complexity and upstream data errors.
Serve as an early tester and internal customer for new data infrastructure tools.
Ethical & Compliant Data Management Follow all applicable privacy, security, and compliance requirements (e.g., HIPAA).

Skills

Strong proficiency in SAS, R, Python, and SQL.
Familiarity with version control (Git) preferred.
Experience with CDISC SDTM/ADaM standards.
Understanding of oncology endpoints (e.g., RECIST, survival analysis) and real world data (RWD) is a plus.
Core Competencies Demonstrated expertise in cleaning and stitching complex datasets.
Ability to work with unstructured text or NLP derived outputs is highly desirable.
Exceptional attention to detail and accuracy.
Strong written and verbal communication skills.
Self directed, curious, humble, and collaborative.

Compensation

Competitive salary range based on experience, qualifications, and location.
Eligible for equity, annual performance bonus, and comprehensive benefits.

Benefits

Eligible for equity, annual performance bonus, and comprehensive benefits.
Qualifications Education BSc or MSc in Statistics, Mathematics, Computer Science, Life Sciences, or a related field.

Apply directly at Harnham →Create a free account for alerts like this View Harnham immigration profile

This listing is sourced directly from Harnham's careers page and normalized into a canonical job model.