Senior Data Scientist (Imaging)

The opportunity

Relation is offering an outstanding opportunity for a Senior Data Scientist to help build the next generation of generative and predictive models of cellular behaviour, with a focus on high-content imaging. Your work will be central to our mission to understand and control cellular decision-making, enabling novel therapeutic strategies grounded in generative models.

You'll be joining a team with access to cutting-edge multiomic and interventional datasets, advanced computational infrastructure, and deep interdisciplinary expertise, and a culture that embraces modern ML tooling, including agentic workflows, to accelerate research iteration.

The role exists to drive imaging data science: curate training-ready imaging datasets, design evaluation that distinguishes biological signal from technical artefact, interpret foundation-model behaviour on cellular imaging, and provide the wet lab interface for the imaging assay teams that generate the data.

Day to day, you will

• Curate training-ready imaging datasets across cell painting and brightfield assays.

• Drive evaluation design for imaging modalities in close partnership with ML and data scientists.

• Surface what models learn about cellular morphology, identify failure modes, and feed findings back into modelling decisions.

• Partner with wet lab assay teams from plate design through to data delivery, ensuring imaging assays remain analytically tractable and yield valuable data.

• Contribute to multi-modal evaluation: link imaging readouts to single-cell and perturbation data.

• Communicate methodology and findings clearly and rigorously across the computational team.

• Track developments in foundation models for biological imaging, and bring relevant advances into our work.

Professionally, you will have

• A PhD (or equivalent industry experience) in computational biology, bioinformatics, computer vision, biomedical engineering, or a closely related discipline.

• Strong fluency with high-content imaging modalities, including cell painting and brightfield: knowledge of what good data looks like, recognition of common artefacts, and judgement on biological relevance.

• Working knowledge of deep learning approaches to imaging, sufficient to reason about model behaviour and design appropriate evaluation.

• Experience designing or contributing to evaluation frameworks for ML models, ideally with imaging or comparable scientific image data.

• Strong Python data-science stack (numpy, pandas / polars, scikit-learn, PyTorch).

• Familiarity with terabyte-scale imaging data and standard scientific formats.

• Strong biological grounding and the ability to partner effectively with wet lab scientists.

• Bonus experience: familiarity with classical bioimage tooling (CellProfiler, scikit-image, ImageJ / Fiji) for QC reference; large public cell painting datasets; publication record in relevant venues.