Data Scientist

Redwood City, CA (Hybrid potentially remote options)

No Sponsorship Available

We are seeking a Clinical Data Scientist to play a pivotal role in transforming complex clinical datasets into high‑quality, analysis‑ready outputs used to support clinical trials and real‑world evidence initiatives.

In this role, you will operate at the intersection of data science, clinical research, and statistical programming
. You’ll be responsible for validating, cleaning, and structuring data originating from multiple sources—including expert manual abstraction teams, AI‑assisted pipelines, EMR feeds, and EDC systems.

You’ll collaborate closely with Clinical Operations, Data Engineering, and AI/ML teams to ensure accuracy, traceability, and compliance across every dataset delivered internally or externally.

This role is ideal for someone who is detail‑obsessed, technically versatile, and passionate about elevating the quality of clinical data used in drug development.

• Convert raw, manually abstracted, and AI‑processed datasets into standardized formats (e.g., CDISC SDTM/ADaM) or client‑specific data models.
• Ensure outputs meet quality, compliance, and traceability standards.
• Generate TLFs (Tables, Listings, Figures) for clinical reports and interim analyses using SAS, R, or Python
  .
• Perform robust data cleaning and QC checks.
• Investigate anomalies and troubleshoot issues across the data pipeline.
• Distinguish between upstream extraction issues and true clinical variations.
• Partner with Data Platform and AI teams to automate cleaning scripts, validations, and workflow logic.
• Serve as an early user and feedback partner for internal data tools.
• Maintain documentation for data derivations, specifications, and validation logic (e.g., Define.xml, Reviewers Guides).
• Support compliance and regulatory submission needs.
• Complete internal and external analysis requests to support clinical insights, client value, and platform performance.
• Apply HIPAA-aligned data safeguards and adhere to best practices across privacy, security, and data governance.

• Education:
• BSc/MSc in Statistics, Mathematics, Computer Science, Life Sciences, or related field.
• Experience:
• 2–5+ years in clinical data science, statistical programming, or data management in pharma/biotech.
• Technical Strengths:
• SAS, R, Python, SQL
• Experience with Git/version control preferred
• Industry Knowledge:
• Familiarity with clinical trial workflows
• Strong understanding of CDISC SDTM/ADaM
• Oncology endpoints (RECIST, survival) and RWD experience is a plus
• Comfort “stitching together” messy, real‑world clinical datasets
• Experience with unstructured text or NLP outputs is desirable