Sr. Director, Data Science, Patient Identification

Role Summary

Sr. Director, Data Science, Patient Identification — lead a data science function focused on identifying undiagnosed rare-disease patients and targeting healthcare providers. Develop AI/ML and statistical approaches using real-world data to detect disease patterns, shape data strategies, and drive decisions across the rare disease portfolio. This role involves strategic leadership, cross-functional collaboration, and delivering data-driven patient outcomes. Location: 3 days per week in the San Francisco/Palo Alto area.

Responsibilities

• Spearhead a high-performing data science function focused on patient identification and provider targeting
• Identify, source, and integrate data assets to find rare-disease patients and treat HCPs; define vision, priorities, and success metrics across multiple programs
• Architect scalable analytical solutions using real-world data (claims, EHR, genomics, lab data, imaging, registries)
• Define the roadmap for AI/ML innovation with production-grade reliability
• Foster a collaborative, mission-driven culture with enterprise-wide data and data science impact
• Design predictive models and patient-finding tools using real-world data; apply NLP and LLM techniques to unstructured EMR data
• Pioneer methodologies in AI/ML for patient identification and run experiments to compare approaches
• Build frameworks for model monitoring, retraining, and evaluation in real-world deployments
• Deploy supervised and unsupervised models for patient finding, diagnostic acceleration, and disease progression; translate insights into actionable field strategies
• Develop robust data pipelines, governance, and scalable model-serving infrastructure
• Evaluate and integrate third-party data to enhance model accuracy and reach
• Collaborate with external vendors and internal teams to operationalize analytics across the portfolio
• Promote reproducibility, version control, and MLOps best practices
• Partner with Commercial, Medical Affairs, and Computational Genomics to integrate insights into decision-making
• Engage with key opinion leaders and data partners to identify early signals for models
• Establish program KPIs, dashboards, and reporting to track performance and improve model accuracy
• Ensure HIPAA, privacy, and ethical data governance compliance
• Manage external vendors and partnerships to expand analytics capabilities

Qualifications

• Required: 10+ years of experience in data science or analytics within biotech/pharma; 3+ years in a leadership role
• Required: Expertise in real-world data analytics, patient identification, and segmentation across multiple therapeutic areas; experience with large-scale real-world data (claims, EMR/EHR, genomics, registries, or wearables)
• Required: Experience developing and deploying sophisticated ML/statistical models using large-scale health data; strong Python, R, SQL, TensorFlow, PyTorch skills; knowledge of feature engineering, model explainability, and ML pipeline automation
• Required: Proven success translating analytics into actionable strategies that drive measurable patient or business outcomes
• Required: Bachelor's degree in data science, computer science, statistics, or related quantitative field
• Required: Experience in rare disease analytics or patient-finding programs supporting commercial launches or diagnostic initiatives
• Preferred: Advanced degree (PhD, MS, MPH) in data science, biostatistics, computer science, or related field
• Preferred: Familiarity with generative AI, LLMs, or graph-based learning in healthcare/biomedical data

Skills

• Real-world data analytics
• ML/Statistical modeling at scale (Python, R, SQL, TensorFlow, PyTorch)
• NLP and LLM techniques for unstructured clinical data
• Model monitoring, retraining, and MLOps
• Feature engineering, model explainability, and ML pipeline automation
• Data governance, data pipelines, and integration of heterogeneous data sources

Education

• Bachelor’s degree in data science, computer science, statistics, or related quantitative field
• Preferred: PhD, MS, or MPH in relevant field