The Computational Toxicology group is dedicated to advancing in-silico approaches that improve the prediction and mechanistic understanding of drug safety across small molecules, biologics, and emerging modalities. This role sits at the intersection of biological science and computational innovation — and that intersection is intentional.

We are looking for a scientist with deep domain knowledge in biology who has also developed computational skills to independently design, build, and deploy data-driven solutions. The ideal candidate can stand at the bench conceptually, understand what drives experimental variability, and architect computational solutions that reflect biological reality.

The role focuses on integrating diverse data sources — including pharmacology, toxicology, genomics, pathology, chemistry, and clinical datasets — into predictive and interpretable models. You will work directly with research scientists to understand their workflows, co-design solutions, and build tools that make computational capabilities accessible to generalist scientists across Development Sciences.

Responsibilities

• Serve as a scientific translator between wet-lab researchers and computational infrastructure — understanding experimental design, data provenance, and biological context well enough to ensure fit-for-purpose solutions
• Engage directly with scientists to understand existing laboratory and analytical workflows, identify bottlenecks, and co-design computational solutions that are practical, reproducible, and scalable.
• Develop user-friendly tools, pipelines, and applications designed for scientists without a computational background, enabling broader Development Sciences teams to leverage computational insights
• Partner with research scientists, data scientists, and safety experts to design, implement, and validate machine learning/AI strategies that address key discovery and preclinical safety questions.
• Curate, harmonize, and integrate multi-modal datasets including chemical, genomic, molecular, in vitro, pathology, and clinical sources, into scalable workflows that support safety insight generation and risk prediction
• Translate computational findings into predictive models, analytical tools, and user-friendly applications that support decision-making in drug discovery and development.

Clearly communicate methods and results to multidisciplinary stakeholders, tailoring messages for both technical and non-technical audiences