Associate Director, Data Science, Computational Oncology

In This Exciting Role, You Will

• Analyze large-scale oncology datasets, including bulk RNA-seq, whole-exome and whole-genome sequencing (WES/WGS), and single-cell RNA-seq (scRNA-seq), to understand disease biology and the mechanisms of disease progression and drug action.
• Analyze functional genomics and perturbational screens, including pooled and arrayed CRISPR screens and Perturb-seq, from QC and hit calling through biological interpretation, to establish target dependency and mechanism for programs across therapeutic areas.
• Nominate and prioritize drug combinations for both oncology and immunology disease areas by weighing expression profiling, disease biology, mechanistic and functional-genomics evidence, and the competitive landscape together, and bring that evidence to program teams across the portfolio.
• Apply rigorous statistics and integrate multi-omics and functional genomics data with prior biological knowledge, using network-based and machine learning approaches, to reach robust conclusions and a coherent picture of target and pathway biology.
• Apply deep learning and single-cell foundation models to problems such as cell-type deconvolution, batch integration, patient stratification, and perturbation-response prediction.
• Use modern AI, including LLM-based agents and retrieval over internal data, to accelerate evidence synthesis and analysis, and help bring these tools into routine, well-validated use.
• Draw on human and real-world data to inform and reverse-translate discovery hypotheses, connecting preclinical findings to patient biology.
• Collaborate closely across disciplines, including experimental scientists, AI and ML and data science teams, software engineers, and program teams, and set a high bar for reproducible, well-documented research that supports Discovery Oncology.

Minimum Requirements

• A PhD in computational biology, bioinformatics, biostatistics, genetics/genomics, computational biology, mathematics, computer science, biophysics, computational chemistry or a related quantitative STEM discipline and 4+ years of relevant experience; MS and 8+ years of relevant experience; OR BS and 12+ years of relevant experience.
• A passion for solving problems in oncology and cancer genomics through computational methods, with a consistent focus on detail and execution.
• Deep experience analyzing and biologically interpreting large-scale NGS datasets (bulk RNA-seq, WES/WGS, scRNA-seq), including experimental design, QC, and building analyses where no standard pipeline exists, and integrating multiple omics layers with prior biological knowledge.
• A strong statistical foundation, spanning hypothesis testing, regression and mixed models, survival analysis, and dimensionality reduction, with sound judgment about confounding, batch effects, and multiple comparisons, and a track record of applying machine learning to biological data with judgment about where it adds value and where simpler methods suffice.
• Strong technical skills, including R or Python, version control (Git), and Linux, with hands-on experience across cloud and data platforms such as AWS (S3), Nextflow, Databricks, and Posit.
• Familiarity with major cancer genomics resources, such as TCGA, GTEx, CCLE, CPTAC, and DepMap.
• A collaborative working style and excellent oral and written communication skills.

Preferred Experience and Skills

• A Ph.D. in Bioinformatics, Biostatistics, Computational Biology, Statistics, Computer Science, Genetics, Mathematics, or a related field.
• Post-doctoral or relevant industry experience in cancer genomics or computational oncology, with a deep understanding of cancer biology and current research trends.
• Substantial computational experience with functional genomics data, including CRISPR screen hit-calling frameworks, library design, optical or single-cell screens, and image-based phenotypic profiling.
• Experience applying or fine-tuning foundation models for single-cell or genomic data, and an interest in developing agentic AI and LLM-powered tools for biological analysis.
• Network-based analysis of gene regulatory patterns and signaling pathways from NGS data.
• A strong publication record.