Senior Data Scientist – Single Cell

About the role

RelationRx is a TechBio company developing transformational medicines by leveraging single‑cell multi‑omics, functional assays and machine learning. We are looking for a Senior Data Scientist to build next‑generation generative and predictive models of cellular behaviour, with a focus on single‑cell multi‑omics data.

Key responsibilities

• Process and quality‑control paired single‑cell RNA‑seq and scATAC‑seq data at scale across thousands of perturbations.
• Develop and maintain Nextflow pipelines compatible with custom combinatorial indexing chemistries, using tools such as STARsolo, Alevin‑fry, Chromap and SnapATAC2.
• Integrate scRNA‑seq, scATAC‑seq with extracellular proteomics and high‑content imaging to create multimodal training datasets.
• Manage data in memory‑efficient formats (e.g., Zarr) for GPU‑accelerated processing and model training.
• Partner closely with wet‑lab scientists from experimental design through interpretation to maximise data value.
• Contribute to evaluation frameworks, designing metrics, benchmarks and biological sanity checks for ML models.
• Collaborate with ML modelers on model architecture development and present findings to internal stakeholders.

Required profile

• PhD (or equivalent industry experience) in computational biology, bioinformatics or a related quantitative field.
• Extensive hands‑on experience processing large‑scale single‑cell multi‑omics data, ideally paired RNA + ATAC (10x Multiome or equivalent).
• Proficiency with single‑cell analysis toolkits (e.g., scverse ecosystem) and workflow management frameworks such as Nextflow or Snakemake.
• Experience with arrayed CRISPR perturbation screens, including sample hashing and perturbation‑specific QC.
• Strong Python programming skills and familiarity with high‑performance computing environments.
• Excellent communication skills to bridge experimental and ML teams.

Required skills

• Python
• Nextflow
• Snakemake
• scverse ecosystem (scanpy, scvi‑tools, etc.)
• STARsolo, Alevin‑fry, Chromap, SnapATAC2
• Zarr data format
• GPU‑accelerated processing
• High‑performance computing
• CRISPR perturbation screen analysis
• Single‑cell RNA‑seq and scATAC‑seq analysis
• Multimodal data integration (proteomics, imaging)