#R-221333
odel outputs into clear business-facing summaries to enable decision-making by commercial and brand teams.
Contribute to the design of pilots, A/B tests, and analytic frameworks to support test-and-learn strategy.
Develop, validate, and maintain machine learning models using Python, PySpark, and Databricks across large longitudinal datasets.
Maintain best practices in model versioning, QC, documentation, and reproducibility using MLflow and Git.
Collaborate with brand partners, global analytics, and engineering teams to ensure seamless model deployment and interpretation.
Thrive | What you can expect
As we work to develop treatments that take care of others, we also work to care for our teammates' professional and personal growth and well-being.
Basic Qualifications
Master's degree in Data Science, Computer Science, Public Health, or related field.
7-14 years of hands-on experience in predictive modeling, machine learning, or healthcare analytics.
Strong programming skills in Python and SQL, with experience using Databricks or similar platforms.
Solid grasp of experimentation methods including causal inference, uplift modeling, and A/B testing.
Experience working with patient-level or longitudinal healthcare data (e.g., claims, EMR, lab).
Preferred Qualifications
Experience in life sciences, pharma, or regulated health analytics environments.
Familiarity with MLflow, AWS, Git, and DevOps-style model deployment workflows.
Understanding of patient journey analytics and use cases such as HCP segmentation or patient triggers.
Exposure to RAG/LLM applications in data science is a plus.
Strong communication skills and ability to work across technical and business stakeholders.
.