AI/ML Technical Expert – Predictive safety & multimodal biology

We have an exciting opportunity for a a scientifically rigorous and innovative AI/ML Technical Expert to advance predictive safety and strengthen early research decision-making through data-driven and mechanistic approaches. Within the role working at the interface of biology, computational science, and artificial intelligence you will translate priority safety questions into robust modelling strategies, interpretable insights, and scalable analytical capabilities. The role will contribute to the development of a predictive safety framework that enables earlier identification of risk, improves mechanistic understanding, and enhances the quality and confidence of decision-making across research programs. Key responsibilities will include: - Partnering with toxicologists, biologists, chemists, bioinformaticians, and data scientists to define priority questions for predictive safety. - Leading the development and evaluation of advanced AI/ML methodologies and predictive modelling approaches to address strategic safety questions. - Applying machine learning, artificial intelligence, statistical modelling, and knowledge-driven approaches to extract meaningful biological signals (such as mechanisms of toxicity, AOPs, and safety-related outcomes) from large, complex, and heterogeneous datasets. - Translating modelling outputs into actionable scientific insight that supports project and portfolio decisions. - Evaluating Evaluate emerging AI, modelling, and computational-biology methods, while identifying applications that offer practical scientific value. - Communicating complex computational findings clearly and credibly to multidisciplinary audiences. What we are looking for - PhD (or equivalent experience) in Computational Biology, Bioinformatics, Systems Biology, Computational Toxicology, Data Science, Computer Science, Biomedical Engineering, or a related discipline. - Demonstrated experience integrating diverse biological data types and extracting meaningful biological insight from complex, high-dimensional datasets. - Strong programming skills in Python and experience with modern data science and machine learning frameworks. - Proven experience in developing, validating and applying AI/ML, statistical, or computational biology approaches to address biological questions, while building reproducible computational workflows, analytical pipelines, and scientific software tools. - Self-starter with enthusiasm, flexibility and desire to learn and apply new skills. Desirable Experience - Experience in computational toxicology, predictive safety, agrochemical research, pharmaceutical discovery, environmental science, or another applied research setting. - Familiarity with adverse outcome pathways, mode-of-action frameworks, systems toxicology, network biology, or causal inference. - Experience with chemical informatics, molecular descriptors, structural alerts, read-across, QSAR, or exposure- and hazard-modelling approaches. - Background in applying AI to biological or toxicological data, including multimodal learning, graph-based methods, foundation models, or representation learning with experience in using phenotypic imaging, cell painting, transcriptomic, metabolomic, or other molecular data as supporting evidence for model development or mechanistic interpretation.