Research Fellow in Spatial Biology

We are seeking a computational scientist with a strong machine learning background to develop new methods for spatial transcriptomics (ST). Working within the Wellcome-funded bioimaging programme, you will design, implement and validate AI and mathematical approaches that turn high-dimensional spatially resolved molecular data from platforms such as 10x Xenium into quantitative descriptions of tissue organisation and disease. The role focuses on building models and frameworks that treat tissue as a spatial and geometric object. We are particularly interested in bringing ideas from geometric and unsupervised deep learning, spatial statistics and topology to bear on how cells organise into neighbourhoods, how they interact, and how these local patterns give rise to tissue architecture. You will also lead work on integrating ST with digital pathology and clinical imaging, linking molecular, cellular and organ-level scales. You will join a multidisciplinary team at King's and partner institutions, where computational scientists and mathematicians work alongside pathologists, clinicians and experimental biologists. A central part of the role is turning biological and clinical questions into well-posed computational problems, and making sure the resulting methods are robust, reproducible and able to scale on high-performance computing. We expect you to build an independent research profile, publishing your methods in leading venues and sharing them as open-source software, while helping to shape new grant applications and supervising PhD students and junior researchers. This is a full time and you will be offered an a fixed term contract until 31 March 2031.

To be successful in this role, we are looking for candidates to have the following skills and experience: Essential criteria

• A PhD in a quantitative discipline (e.g. computer science, mathematics, statistics, physics or engineering), or in computational biology with a strong methodological component.
• A track record of developing novel AI/machine-learning or mathematical/statistical methods, shown by publications in peer-reviewed journals or leading machine-learning conferences.
• Significant experience modelling spatially defined data, ideally imaging-based spatial transcriptomics (e.g. Xenium).
• Strong expertise in modern machine learning (e.g. graph neural networks, representation/self-supervised learning, generative models), with proficiency in Python and a deep-learning framework such as PyTorch.
• Experience developing reproducible, scalable and open-source research software, including on high-performance and GPU computing.
• A proven ability to lead research projects, collaborate with academic partners and supervise researchers.
Desirable criteria
• Expertise in topological and geometric approaches to tissue architecture, such as persistent homology, discrete curvature and Ricci flow, graph Laplacians and spectral methods, or optimal transport.
• Experience in spatial statistics (e.g. point processes, spatial autocorrelation, Gaussian processes) or probabilistic modelling of spatial data.
• Experience integrating multimodal or multiscale data, e.g. spatial transcriptomics with H&E/digital pathology, multiplexed imaging or MRI, including use of pathology or single-cell foundation models.
• Experience with image-level processing of spatial data, such as cell segmentation and denoising.
• Experience presenting complex quantitative methods to multidisciplinary audiences and mentoring researchers from non-computational backgrounds.
  
  The Faculty of Life Sciences & Medicine at King's College London seeks to appoint a Research Fellow in the Comprehensive Cancer Centre, which is the academic arm of one of the leading cancer centres in Europe bringing together world-class clinical services delivered by our NHS partners, with research and education for the benefit of cancer patients in South East London and beyond.
The Wellcome project to accelerate cutting-edge bioimaging technology development, is a five-year cross-disciplinary programme, led by Professor Maddy Parsons from the School of Basic & Medical Biosciences. It will develop pioneering approaches to enable the creation of full molecular 'maps' of disease tissue, spanning multiple scales from whole organ down to individual molecules. The programme will combine MRI-based clinical imaging of patients with emerging spatial methods that capture the underlying cellular and molecular activity within tissues in intricate detail. By combining data from these diverse imaging approaches using advanced computational and AI-driven tools, the team aim to reveal how cells interact with their environment and how these interactions drive disease., We pride ourselves on being inclusive and welcoming. We embrace diversity and want everyone to feel that they belong and are connected to others in our community. We are committed to working with our staff and unions on these and other issues, to continue to support our people and to develop a diverse and inclusive culture at King's. We ask all candidates to submit a copy of their CV, and a supporting statement, detailing how they meet the essential criteria listed in the advert. If we receive a strong field of candidates, we may use the desirable criteria to choose our final shortlist, so please include your evidence against these where possible. To find out how our managers will review your application, please take a look at our ' ' pages. Interviews are due to be held: TBC