Senior Data Scientist, Epidemiology & RWE Analytics - FSP

Senior Data Scientist Dublin, Ireland Hybrid/Site based You will design, execute, and deliver rigorous, decision-relevant real-world evidence analyses while helping to advance a scalable, AI-enabled analytics capability. This is a hands-on role that combines epidemiological expertise, advanced analytics, and data science to deliver high-quality evidence and actionable insights. The successful candidate will bring deep expertise in epidemiology, analytical programming, observational research, statistical methods, and real-world data. Working closely with the Head of Rapid Analytics and stakeholders across the EpiRWE therapy areas, including Virology, Oncology, and Inflammation, you will translate evidence needs into fit-for-purpose study designs, analytical requirements, executable plans, and high-quality results. You will also identify opportunities to enhance the delivery of EpiRWE analytics through automation, reusable analytical assets, and agentic workflows. In partnership with dedicated AI and Data Engineers responsible for building and maintaining the underlying technical infrastructure, you will help define scientific and analytical requirements, guide implementation, validate outputs, and ensure technology-enabled workflows remain scientifically robust, reproducible, and valuable to stakeholders. Key Responsibilities EpiRWE Analytics Delivery Partner with stakeholders to define evidence needs and translate them into clear research questions and analytical plans using OMOP and native datasets (e.g., EMR, claims, and molecular data). Design, execute, interpret, and report observational and epidemiologic studies supporting assigned assets, indications, and therapeutic areas. Conduct feasibility analyses, methodology development, statistical analysis planning, cohort definition, programming, quality control, results interpretation, and final reporting. Ensure that analytical approaches are scientifically rigorous, fit for purpose, and aligned with the clinical, medical, regulatory, safety, or access decision being supported. Provide guidance on study design, data-source selection, epidemiologic methods, potential biases, confounding, sensitivity analyses, and interpretation of findings. Study Design and Analytical Methods Apply advanced observational research methods to address complex research questions. Evaluate assumptions, limitations, data completeness, measurement validity, confounding, selection bias, and generalizability. Develop and review table shells, analytic data specifications, statistical analysis plans, derived variables, statistical models, and quality-control strategies. Perform and oversee analyses using R, SQL, and Python. Apply version control (GitHub) and reproducible research practices to analytical code, cohort definitions, specifications, documentation, and study outputs. OMOP CDM, OHDSI, and Federated Analytics Support the scientific and analytical use of the OMOP Common Data Model and the OHDSI ecosystem for rapid, standardized, and reproducible real-world evidence generation. Translate study requirements into standardized concepts, concept sets, cohort definitions, temporal logic, inclusion and exclusion criteria, and analytical specifications. Use and adapt OHDSI open-source tools and methods to support cohort development, cohort diagnostics, characterization, feasibility assessment, and multi-database analytics. Develop reusable cohorts, phenotypes, concept sets, analytical modules, and study packages that can be applied across data sources, therapeutic areas, and research questions. Support federated analytics by developing portable and well-documented study specifications that can be executed by approved data partners without transferring patient-level data. Evaluate cross-database differences in coding, data capture, observation time, population characteristics, and analytical results. Data-Source Evaluation and Feasibility Conduct feasibility assessments to match research objectives with the most appropriate real-world data sources, including claims, electronic health records, registries, laboratory data, linked datasets, and patient-generated data. Extend analytical approaches beyond OMOP-based data when registries or other non-OMOP sources are better suited to the research question. Rapid Analytics and Automation Identify opportunities to improve EpiRWE delivery through automation, reusable workflows, structured analytical specifications, and AI-enabled tools. Define how reusable tools, agents, and human review checkpoints can support efficient and scalable analytical workflows. Translate epidemiology and RWE needs into technical requirements, user stories, acceptance criteria, solution designs, and delivery priorities for engineering partners. Partner with AI, data, and software engineers to develop solutions supporting concept-set development, cohort construction, feasibility analyses, cohort diagnostics, quality control, documentation, and analytical reporting. Define validation criteria and quality standards for automated workflows and AI-enabled solutions. Review and validate AI-generated or automated outputs for scientific accuracy, completeness, consistency, traceability, and alignment with study protocols. Ensure that automation enhances analytical quality, efficiency, and scalability while maintaining appropriate scientific oversight. Capability Building and Stakeholder Impact Help establish EpiRWE analytics as a scalable organizational capability rather than a collection of one-off studies. Develop reusable templates, analytical standards, cohort libraries, study packages, quality-control frameworks, and documentation practices. Measure capability value through improvements in delivery speed, analytical quality, reproducibility, reuse, stakeholder adoption, and decision impact. Promote a culture of continuous improvement that challenges inefficient processes while maintaining scientific rigor and appropriate governance. Contribute to the development of analytical best practices, reusable assets, and evidence-generation approaches across EpiRWE and cross-functional teams. Required Qualifications Advanced degree in Epidemiology, Biostatistics, Health Services Research, Outcomes Research, Public Health, Biomedical Informatics, Data Science, or a related quantitative field. Demonstrated expertise in epidemiologic study design, statistical analysis, causal inference, and the evaluation of bias and confounding. Experience working with healthcare claims, EHR, registry, laboratory, linked, or other real-world data sources. Hands-on analytical programming experience using R, SQL, and Python. Experience developing and applying machine learning, AI, or advanced analytical methods to real-world data and evidence-generation use cases. Experience with version control and reproducible analytical workflows. Ability to translate scientific questions into protocols, analysis plans, analytical specifications, technical requirements, and delivery plans. Strong understanding of data quality, analytical validation, quality control, traceability, and documentation. Ability to communicate complex analytical findings clearly to both technical and non-technical stakeholders. Why Join? Those who join us become part of a recognized global leader still willing to cha