Principal RWE Biostatistician FSP

Overview

In this role, you lead advanced RWE analyses to inform clinical development, regulatory strategy, and payer decisions. You work embedded with a global pharma client, collaborating with cross-functional teams to translate complex quantitative findings into actionable insights. You apply causal inference and ML methods to large healthcare datasets, and you ensure regulatory-ready, scientifically rigorous outputs. This position offers impact across game-changing studies and scalable analytics in a matrixed environment.

Responsibilities

• Lead and support advanced RWE analyses using large-scale real-world data to inform clinical development, regulatory strategy, HEOR, and payer decisions
• Review statistical analysis plans and provide input for observational studies and target trial emulations using diverse data sources
• Apply causal inference and statistical learning methods (e.g., propensity scores, inverse probability weighting, survival and longitudinal models, representation learning) to address confounding and missing data
• Develop and implement machine learning pipelines for prediction, patient stratification, phenotyping, and NLP on structured and unstructured data
• Combine AI/ML outputs with traditional statistics to support interpretability and regulatory readiness
• Build scalable, reproducible analytical workflows in Python and/or R with proper software engineering and QC
• Collaborate with clinical scientists, epidemiologists, data engineers, and HEOR to define fit-for-purpose analytic strategies
• Translate complex quantitative findings for technical and non-technical stakeholders
• Support governance readiness, regulatory submissions, audits, and scientific dissemination
• Deliver high-quality outputs on time within a global, matrixed FSP environment

Key requirements

• Strong grounding in mathematical statistics, probability, and statistical modeling
• Experience applying machine learning or AI methods to large or high-dimensional datasets
• Proficiency in SAS, R and Python; familiarity with ML frameworks (scikit-learn, PyTorch, TensorFlow) preferred
• Solid understanding of causal inference and observational study design
• Experience with large-scale real-world data (administrative claims, EHR, OMOP/CDM, registries)
• Familiarity with cloud or big-data environments (SQL, Spark, Databricks, AWS, Azure, GCP)
• Experience with Bayesian modeling or probabilistic machine learning
• Publications or applied research in ML + healthcare or RWE
• Interest in translating academic ML into regulatory-grade analytics
• Excellent communication and ability to collaborate in cross-functional, global teams

• excellent communication
• collaboration in cross-functional, global teams
• ability to translate complex results for non-technical stakeholders
• SAS, R, Python
• machine learning frameworks: scikit-learn, PyTorch, TensorFlow
• causal inference methods

…