Senior Scientist – Translational Safety, Risk Sciences

Responsibilities

• Lead efforts to develop and integrate modern data infrastructure, analytics platforms, and visualization capabilities to support New Approach Methodologies (NAMs) and broader translational safety initiatives across the organization.
• Design, develop, and maintain scalable data infrastructure and visualization solutions supporting NAMs initiatives and other TSRS workflows
• Develop and implement databases and registries using tools such as Databricks
• Collaborate with cross-functional partners, including scientific, data engineering, IT, and AI/ML teams to harmonize and standardize data structures across nonclinical and clinical safety domains.
• Define metadata standards and ontology mappings for model systems, assays, samples, readouts, validation status, and context of use
• Support data governance, data quality, and reproducibility best practices across TSRS platforms
• Conceptualize, design, and build interactive dashboards and visualizations using platforms such as Spotfire to enable AI-supported and data-driven decision-making
• Translate complex scientific and technical concepts into clear visualizations and actionable insights for diverse stakeholders
• Develop pipelines and workflows to integrate NAMs data and other internal data with enterprise datasets, such as clinical data, via AI/ML
• Apply AI/ML approaches to support translational safety analyses, predictive modeling, and emerging NAMs applications

Requirements

• Doctorate degree PhD OR PharmD OR MD (and relevant post‑doc where applicable) OR Master’s degree and 3 years of Scientific and/or Data Science experience OR Bachelor’s degree and 5 years of Scientific and/or Data Science experience
• Experience developing data infrastructure and analytics solutions in Databricks environments
• Knowledge of relational databases, data engineering workflows, and cloud‑based analytics platforms
• Strong expertise in Spotfire dashboard development and data visualization
• Experience working with SharePoint‑based scientific collaboration and data environments and integrating data across multiple platforms such as Benchling, SharePoint, Databricks, Spotfire, or other LIMS or ELN systems
• Experience integrating heterogeneous datasets, including clinical datasets and other structured or unstructured internal and external/public datasets
• Experience defining data models for complex biological entities such as NAMs and advanced model systems, including disease‑relevant models, assays, and associated datasets
• Strong understanding of FAIR data principles, metadata standards, controlled vocabularies, ontologies, and data governance
• Familiarity with NAMs, complex in vitro models, translational in vitro/in silico platforms, toxicology, and/or translational safety approaches
• Understanding of target discovery, translational biology, nonclinical safety, drug discovery, and/or drug development processes
• Strong communication and collaboration skills with the ability to work effectively across multidisciplinary teams and actively identify opportunities to link people, models, datasets, tools, and decisions
• Demonstrated ability to manage multiple priorities in a fast‑paced scientific environment.