Senior Principal Investigator - Spatial Multiomics (m/f/d)

<p></p><p>At GSK, our mission is to improve the quality of human life by enabling people to do more, feel better, and live longer. We are a science-led global healthcare company with a special purpose: to help people do more, feel better, live longer.</p><p></p><p>We are seeking a <b>Senior Principal Investigator - Spatial Multiomics (m/f/d)</b> with extensive expertise in Machine Learning (AI/ML) and computer vision applications to histology and spatial biology to lead the development and deployment of deep learning solutions to transform raw histological images and spatial omics datasets (spatial transcriptomics, proteomics, and metabolomics) into biologically interpretable, analysis-ready data for drug discovery and disease phenotyping. The candidate will architect end-to-end machine learning pipelines and play and crucial role in data processing workflows <span>across different</span> tissues, applying modern AI/ML frameworks specifically to tissue microenvironment analysis, cell-cell interaction modeling, and disease phenotype prediction that inform target discovery and the development of complex <i>in vitro</i> models.</p><p></p><p>This role requires hands-on expertise working at the intersection of computational biology and artificial intelligence, combining deep biological understanding with practical AI/ML engineering skills, and the ideal candidate will have a strong background in data pipelines for applied machine learning, digital pathology, histology and tissue biology.<br/><br/><b>Key Responsibilities:</b></p><ul><li><b>Lead the development and deployment of advanced machine learning pipelines</b> to transform raw histological images and spatial omics datasets into quantitative, biologically interpretable insights that directly inform target validation strategies and drug discovery decision-making.</li><li><b>Design and implement end-to-end computational workflows</b> for processing multi-modal spatial data (transcriptomics, proteomics, metabolomics) across diverse tissue types, ensuring robust data quality, reproducibility, and scalability to support high-throughput target screening and validation programs.</li><li><b>Design and execute specialsed generative AI/ML approaches</b> for tissue microenvironment characterisation, cell-cell interaction modeling, and disease phenotype prediction that generate quantitative evidence packages for target prioritization, mechanism of action studies, and therapeutic hypothesis generation.</li><li><b>Collaborate closely with biology, analytical, and clinical teams</b> to translate computational findings into actionable target validation datasets, including biomarker identification, patient stratification strategies, and <i>in vitro</i> model development that support go/no-go decision-making for drug development programs.</li><li><b>Establish and maintain cutting-edge methodological capabilities</b> by staying current with advancements in spatial multiomics, digital pathology, and AI/ML frameworks, continuously evaluating and implementing new technologies to enhance the depth and reliability of target validation data packages.</li><li><b>Drive cross-functional integration</b> of spatial omics insights into broader disease phenotyping and target discovery workflows, ensuring seamless data flow and interpretation across research platforms to maximise the impact of computational analyses on drug discovery outcomes.</li><li><b>Communicate complex analytical results and their implications</b> to diverse internal and external stakeholders through compelling data presentations, peer-reviewed publications, and scientific conference presentations that effectively convey the value of spatial biology approaches in target validation.<br/> </li></ul><p><b>Qualifications:</b></p><ul><li>PhD in a relevant field (e.g., Computational Biology, Systems Biology, Biology, Medicine) with a strong emphasis on machine learning and spatial multiomics.</li><li>Full command of programming languages with emphasis on the Python ecosystem.</li><li>Extensive experience in spatial omics data processing workflows.</li><li>Proven track record in disease phenotyping and digital pathology through peer-reviewed publications and/or AI/ML conferences.</li><li>Expertise in applied machine learning workflows, particularly pytorch and pytorch-geometric is essential.</li><li>Strong analytical and problem-solving skills focused on linking different data modalities to extract disease-specific biological insights.</li><li>Knowledge of coding best practices and documentation (i.e: github, gitlab).  </li><li>Excellent communication and collaboration skills, with the ability to work effectively in multidisciplinary teams.</li></ul><p></p><h1><i><b>Why GSK?</b></i></h1><ul><li>Opportunity to work in a cutting-edge scientific environment with access to state-of-the-art technologies.</li><li>Collaborative and inclusive culture that values innovation and scientific excellence.</li><li>Competitive compensation