Principal Statistical Methodologist, Raleigh, NC

UCB•Raleigh, NC

10d•Hybrid

About The Position

This role is for a Principal Statistical Methodologist within the Statistical Innovation team in Biometric and Data Sciences (BDS). The position is based in Raleigh, US. The individual will shape evidence generation, modeling, and communication throughout the drug development lifecycle by applying modern computational and machine-learning methods to R&D decisions. Responsibilities include developing and applying advanced data-driven and model-based approaches using statistics, machine learning, and AI, translating them into reusable tools, and collaborating across functions to implement them in drug development decision-making. The role also involves contributing to the group's scientific profile through publications and external collaborations.

Requirements

Doctoral degree in statistics, biostatistics, mathematics, computer science with a strong quantitative/statistical component, or a closely related discipline with a solid grounding in statistical inference and uncertainty.
3+ years of experience within the pharmaceutical industry.
Strong, multi-language scientific programming skills (R and Python preferred; software-engineering practices such as version control, testing, and reproducible workflows a clear advantage).
Demonstrated expertise in machine learning and/or AI methods, with hands-on experience applying them to real problems.
Sound knowledge of ICH guidelines and understanding of regulatory requirements from major health authorities.
Ability to work effectively with autonomy, manage multiple priorities, and deliver timely, high-quality outputs.
Clear written and spoken communication in English, including the ability to explain technical concepts to non-technical audiences.

Nice To Haves

Experience in advanced computational methodology for clinical development (early to late stage) is an advantage.
Direct entry may be considered.
Experience with large language models, causal inference, synthetic data, or digital-twin/simulation approaches is a strong advantage.

Responsibilities

Develop and apply advanced computational and statistical methods, including machine learning, AI, and scenario evaluation using modern simulation approaches, to inform design, analysis, and decision-making across development.
Build robust, well-engineered, reusable tools and workflows that bring these methods into routine use, with attention to reproducibility and software quality.
Bring a quantitative lens with appropriate rigor to emerging problems such as synthetic and external control data, causal inference, and digital-twin or simulation-based approaches.
Partner with statisticians and cross-functional colleagues to identify where computational and data-driven methods add the most leverage, and translate complex approaches into clear insight for technical and non-technical audiences.
Contribute to internal capability building by sharing tools, code, and methods across the team and wider organization.
Contribute to the group's external profile through scientific publications, conference presentations, and participation in cross-industry initiatives and working groups.