About the role

Join our Functional Genomics team to analyze Drug-seq data from high-throughput chemical and CRISPR perturbation screens that drive mechanism-of-action studies and can be used to train AI models . You’ll design and run scalable analyses across thousands of perturbation and cell type combinations, turning raw Drug-seq readouts into robust, reproducible insights. Day to day, you’ll integrate high-throughput results with pathway/ontology annotations, and deliver crisp summaries and figures to wet-lab partners and program teams.This role suits someone eager to apply data science computational biology to high-throughput datasets, delivering analyses that shape compound selection and spark testable hypotheses.

What you’ll do

• Process and analyze Drug-seq transcriptomic datasets from chemical libraries and CRISPR perturbation screens across multiple cell types.
• Perform rigorous QC, normalization, and differential expression (DESeq2/edgeR); aggregate and compare signatures across conditions.
• Build reproducible pipelines (Snakemake/Nextflow; R/Python) and clean analysis notebooks (R Markdown/Jupyter).
• Annotate results with pathways/ontologies (GSEA/fgsea, Enrichr) and public references; generate publication-quality visualizations.
• Collaborate with wet-lab scientists to plan screens, define controls/replicates, and translate findings into actionable follow-ups.
• Contribute curated features/labels that help train and evaluate AI/ML models for MoA/target inference and compound ranking.
• Document methods and results; share concise updates with stakeholders.