Data Scientist

Role & responsibilities

Role: Data Scientist with Pharmaceutical or Healthcare Domain Experience

We are seeking a highly skilled professional to join our Real World Data (RWD) team. This role focuses on building scalable, reproducible data pipelines and diseasespecific datasets that power clinical research, health economics, and outcomes studies. You will collaborate closely with subject matter experts (SMEs), clinicians, and data engineers to translate protocollevel specifications into computable datasets that support oncology and specialty disease research.

Key Responsibilities

• Clinical rule implementation: Translate SMEdesigned clinical rules into scalable, reproducible data pipelines operating against the central data lake.
• Structured and unstructured data integration: Engineer patientlevel features using medical and pharmacy claims, lab results, and NLPderived outputs.
• Diseasespecific dataset development: Build and maintain datasets covering cohort construction, index dating, treatment sequencing, and clinical event labeling.
• Line of therapy algorithms: Develop and apply algorithms that handle realworld complexity including combination regimens, gaps, dose modifications, and offlabel use.
• NLP signal integration: Incorporate diagnosis mentions, staging, biomarker results, and progression language alongside structured claims to enrich dataset completeness.
• Data quality assurance: Produce data quality reports and conduct samplelevel audits to validate clinical logic against source data.
• Collaborative refinement: Work iteratively with SMEs to surface anomalies, identify rule gaps, and refine logic collaboratively.

Required

• 4+ years of experience in data science, biostatistics, or health data engineering within life sciences.
• Proficiency in SQL and Python (or R) for largescale healthcare data manipulation.
• Direct experience with claims data, EMR data, or both in an RWD or HEOR setting.
• Familiarity with NLP outputs and integrating unstructured signals into structured datasets.
• Experience implementing clinical event algorithms from protocollevel specifications.

Preferred

• Experience with cloud data lakes or warehouses (Snowflake, Redshift, Databricks).
• Familiarity with OMOP CDM or other clinical data models.
• Background in oncology datasets or specialty disease datasets.
• Comfort working in a pod model with close clinical collaboration.

Disease Areas
Initial pod coverage will include Breast Cancer, Gastric Cancer, and Multiple Sclerosis, with additional indications prioritized based on client demand. Team members will develop deep expertise in anchor indications while expanding breadth across the portfolio.