Senior Principal Scientist - BioAI; h​/f

Responsibilities

• Lead the design and implementation of AI-driven analytical frameworks for drug target discovery.
• Develop, train, validate, and optimise machine learning and deep learning models on multimodal biological datasets.
• Apply advanced statistical learning, graph-based modelling, and network inference techniques to uncover causal biological mechanisms.
• Establish reproducible computational workflows and robust model evaluation pipelines.
• Perform large-scale data processing and feature engineering on ultra-high throughput in-vitro screening datasets.
• Analyse high-dimensional data (cell painting, transcriptomics, proteomics, metabolomics) using systems biology and computational modelling approaches.
• Build scalable data pipelines for structured and unstructured biological datasets.
• Apply dimensionality reduction, clustering, representation learning, and integrative multi-omics modelling techniques.
• Conduct rigorous benchmarking, validation, and sensitivity analyses to ensure model robustness and biological interpretability.
• Design scalable architectures for multimodal data integration across distributed compute environments.
• Optimise code for performance in high-performance computing (HPC) and cloud environments.
• Contribute to internal AI evaluation frameworks, including metrics for biological plausibility, predictive accuracy, and translational relevance.
• Implement version-controlled, containerised, and production-grade computational solutions.
• Translate complex computational findings into actionable biological hypotheses and drug target candidates.
• Partner with experimental scientists to iteratively refine computational models using wet-lab feedback.
• Influence systems biology strategy by defining computational standards, modelling approaches, and AI governance practices.
• Communicate complex technical insights clearly to scientific, technical, and executive stakeholders.

• Master's degree or PhD in Computer Science, Computational Biology, Bioinformatics, Machine Learning, Systems Biology, or a related quantitative discipline.
• Strong hands-on experience in:
  • Python (Num Py, pandas, PyTorch, Tensor Flow, scikit-learn) and/or R
  • Machine learning and deep learning for structured and high-dimensional data
  • Statistical modelling and causal inference
  • Network biology and graph-based learning approaches
• Experience building scalable data processing pipelines in cloud or HPC environments.
• Proven ability to independently design, implement, and validate computational models in production or research settings.
• Experience integrating multimodal datasets and handling noisy, incomplete biological data.
• Significant experience in pharma, biotech, or tech-bio environments.
• Demonstrated impact in computational drug target identification or translational AI initiatives.
• Experience working in interdisciplinary teams bridging computational and experimental domains.
• Experience applying AI to cardiometabolic disease datasets.
• Background in cellular or molecular biology sufficient to contextualise computational outputs biologically.
• Experience developing interpretable AI frameworks for biomedical decision-making.