Associate Director, Data Science

The Translational Genome Analytics group is recruiting an Associate Director (Associate Principal Scientist) to join its data science team.

Responsibilities

• Perform reverse translation from clinical datasets to enable biomarker discovery, combination strategies, and novel target identification for molecularly defined patient populations.
• Analyze, summarize, and visualize findings from large multi-modal clinico-genomic datasets (bulk RNA-seq, WES/WGS, imaging, epigenetic profiling, single-cell RNA-seq, proteomics).
• Use deep learning/AI and multivariate predictive modeling to discover novel biomarkers predictive of clinical outcomes; apply statistical inference and/or deep learning to integrative analysis of multimodal, high-dimensional tumor profiling data.
• Collaborate with AIML teams developing foundation models trained on large cohorts of human data.

Qualifications

• Master’s (8+ years) or Ph.D. (4+ years) in a quantitative field (e.g., Engineering, Applied Physics/Mathematics, Bioinformatics, Computational Biology) with substantial computational/statistical experience.

Required Experience/Skills

• Statistical learning and data mining expertise for integrative analysis of multimodal, high-dimensional molecular profiling datasets in oncology/immuno-oncology.
• Hands-on experience with large genetic/genomic/immunogenomic/clinical datasets (e.g., IEDB, TCGA, GTEx, DepMap).
• Proficiency coding in R/Python and/or MATLAB with reproducible-analysis best practices.
• Strong communication/presentation skills; ability to guide decisions with data-driven hypotheses.
• Independent, flexible, collaborative mindset.

Preferred

• Clinical-trials genomic analysis; cancer biology knowledge; cross-disciplinary collaboration in matrix environments; high-profile publications.

Skills

• Cancer Biology
• Computational Biology
• Data Analysis
• Data Mining
• Data Science
• Genomic Data Analysis
• Immuno-Oncology
• MATLAB
• Multimodal Analysis
• Python
• R
• Statistical Analysis
• Statistical Learning