Senior Data Scientist (Single Cell)
Core
Build generative and predictive models of cellular behavior using single-cell multi-omics to understand and control cellular decision-making for novel therapeutic strategies.
Role type
Senior IC computational biologist / data scientist (single-cell multi-omics)
Builds
Multimodal training datasets and ML models for cellular decision-making
Domain
Biotech / Drug discovery / Single-cell multi-omics
Deliverable
production ML models
Required skills
Single-cell RNA-seq and scATAC-seq analysis, Nextflow pipeline development, multimodal data integration (proteomics, imaging), Python, high-performance computing, arrayed CRISPR perturbation screen analysis, statistical modelling
Preferred skills
Foundation model development, perturbation prediction models, algorithm development
Technologies
scverse ecosystem, Nextflow, Snakemake, STARsolo, Alevin-fry, Chromap, SnapATAC2, Zarr
Responsibilities
Process and QC paired single-cell RNA-seq and scATAC-seq at scale; Develop and maintain Nextflow pipelines for custom combinatorial indexing chemistries; Integrate scRNA-seq and scATAC-seq with extracellular proteomics and high-content imaging; Manage data in memory-efficient formats for GPU-accelerated processing; Partner with wet lab scientists from screen design to interpretation; Contribute to evaluation frameworks for ML models; Collaborate with ML modellers to develop model architectures; Present findings and methodologies to stakeholders and contribute to publications
Seniority
Senior, hands-on IC
