Data Scientist II

Summary

CareDx is a precision medicine diagnostics company advancing care through molecular diagnostics, digital health, AI-powered data and analytics, and patient support services. The Data Scientist II will develop interpretable AI, machine learning, statistical modeling, and analytics solutions using clinical, laboratory, commercial, and enterprise data, while owning analytical workstreams from research design through validation and deployment support. The role collaborates with clinical, scientific, medical affairs, research, engineering, and business stakeholders to produce reliable insights and decision-support tools.

Responsibilities

• Own analytics and AI workstreams for next-best-action and field education capabilities, translating integrated data into actionable recommendations
• Advance literature intelligence workflows, including search, retrieval, synthesis, evaluation, and validation of AI-generated outputs
• Develop interpretable machine learning, statistical, and generative AI solutions using structured and unstructured clinical, laboratory, commercial, and enterprise data
• Build reproducible workflows and reusable components that can progress from research prototypes to reliable applications and decision-support tools
• Lead analytics research proposals and collaborations, including cohort definition, analysis planning, modeling, interpretation, and communication of results
• Partner with clinicians, scientists, medical affairs, research teams, and business stakeholders to translate questions into rigorous analytical plans and defensible results
• Support abstracts, presentations, and research reports while applying appropriate privacy, security, validation, and documentation practices
• Contribute to and provide backup support for forecasting, Promotion Effectiveness, and Digital Product Impact initiatives
• Perform exploratory analysis, feature engineering, model development and evaluation, sensitivity testing, and scenario analysis using Python or R and SQL
• Collaborate with data and application engineers on pipelines, version control, testing, deployment readiness, monitoring, and maintenance; clearly document data lineage, assumptions, limitations, and recommendations

Skills

• Bachelor of Science (BS) or Master of Science (MS) degree in Data Science, Computer Science, Statistics, Biostatistics, Bioinformatics, or a related quantitative field
• 5+ years of experience in data science, machine learning, advanced analytics, AI engineering, or a related role, including 3+ years in healthcare, diagnostics, biotechnology, clinical research, life sciences, or another regulated environment
• Strong hands-on proficiency in Python or R, SQL, and Git-based development workflows
• Experience developing and validating predictive, descriptive, statistical, or machine learning models using real-world clinical, EHR, laboratory, research, or other complex longitudinal data
• Ability to produce audit-ready documentation covering data lineage, methods, assumptions, testing, validation, and model limitations
• Strong written and verbal communication skills and the ability to collaborate across technical, scientific, clinical, and business teams
• Experience with AI-enabled search, natural language processing, literature intelligence, retrieval-augmented generation, or document synthesis
• Experience moving analytical prototypes into user-facing or production workflows, including testing, monitoring, and ongoing support
• Familiarity with Databricks, cloud data platforms, model lifecycle management, and modern analytics application frameworks
• Experience contributing to clinical research deliverables such as protocols, abstracts, presentations, manuscripts, or analytical reports

Qualifications

Must Haves

• Bachelor of Science (BS) or Master of Science (MS) degree in Data Science, Computer Science, Statistics, Biostatistics, Bioinformatics, or a related quantitative field
• 5+ years of experience in data science, machine learning, advanced analytics, AI engineering, or a related role, including 3+ years in healthcare, diagnostics, biotechnology, clinical research, life sciences, or another regulated environment
• Strong hands-on proficiency in Python or R, SQL, and Git-based development workflows
• Experience developing and validating predictive, descriptive, statistical, or machine learning models using real-world clinical, EHR, laboratory, research, or other complex longitudinal data
• Ability to produce audit-ready documentation covering data lineage, methods, assumptions, testing, validation, and model limitations
• Strong written and verbal communication skills and the ability to collaborate across technical, scientific, clinical, and business teams

Nice to Haves

• Experience with AI-enabled search, natural language processing, literature intelligence, retrieval-augmented generation, or document synthesis
• Experience moving analytical prototypes into user-facing or production workflows, including testing, monitoring, and ongoing support
• Familiarity with Databricks, cloud data platforms, model lifecycle management, and modern analytics application frameworks
• Experience contributing to clinical research deliverables such as protocols, abstracts, presentations, manuscripts, or analytical reports

Benefits

• Incentive compensation
• Health and welfare benefits
• Gym reimbursement program
• 401(k) savings plan match
• Employee Stock Purchase Plan
• Pre-tax commuter benefits
• Additional discretionary bonuses/incentives
• Restricted stock units
• Up to 30 days of paid leave annually for a full-time employee who makes the selfless act of donating an organ or bone marrow