Description
GSK is seeking an experienced Computational Scientist to shape its Spatial Omics and AI capabilities.
You will lead a team developing scalable pipelines and innovative methods for complex single-cell and spatial omics data, enabling deeper insight into disease mechanisms, stronger target hypotheses, and more confident drug-discovery decisions.
Alongside hands-on technical development, you will set scientific direction, establish quality and reproducibility standards, and partner across disciplines to embed these capabilities in research programs and enable their effective use across studies.
Key Responsibilities
- Lead and develop a team of computational scientists, setting scientific priorities and ensuring high-quality delivery.
- Define the analytical strategy for Spatial Omics, establish scalable FAIR data-processing pipelines, and represent the group in cross-functional forums and discussions with senior stakeholders.
- Develop and apply advanced methods for diverse spatial omics (transcriptomics, proteomics, lipidomics, metabolomics) and digital pathology.
- Enable multimodal integration across single-cell, molecular, spatial, morphological, and pathology data.
- Deploy and develop agentic AI workflows that automate processing and orchestrate analyses.
- Partner with experimental scientists, disease biologists, pathologists, and technology teams to inform analytical and scientific strategy.
Basic Qualifications
- PhD in computational biology, data science, or related discipline.
- Strong grounding in disease biology, with the capacity to frame complex scientific questions and interpret multidimensional data in a biologically meaningful context.
- Demonstrated expertise in single-cell and/or spatial omics, supported by practical experience integrating multiple molecular data types.
- Advanced Python proficiency and a record of building reproducible analytical workflows with open-source scientific ecosystems such as scverse.
- Experience developing and deploying agentic scientific workflows at scale.
- Evidence of successful people or technical leadership, including mentoring, capability building, and accountability for team outcomes.
- Strong communication and collaboration skills across computational and experimental disciplines.
Preferred Qualifications
- Advanced experience linking spatial molecular profiles with histology, imaging-derived features, or digital pathology outputs.
- Ability to create data visualizations that communicate complex spatial and multimodal findings to scientific and decision-making audiences.
- Knowledge of machine learning for image analysis, multimodal integration, or predictive modeling in biomedical research.
- Track record of moving methodological innovation into adopted solutions that influence biological insight and drug-discovery decisions.