Director, Data Science, Functional Genomics

MSD•Cambridge, MA

1d•$214,100 - $337,000•Hybrid

About The Position

The Director of Data Science, Functional Genomics will lead the functional genomics analytics function within the Translational Genome Analytics team in the Data, AI and Genome Sciences department. This senior technical and scientific leader will shape how functional genomics evidence is generated, interpreted, and integrated across the discovery portfolio, and own computational and modeling frameworks ranging from perturbational-screen hit calling to multi-evidence integration for target and drug-combination prioritization. The role will set early discovery direction, build and lead a team of scientists, and apply AI and machine learning to accelerate data-driven decisions. The Director will build scalable analytics for pooled, arrayed, single-cell, and optical CRISPR screens; develop methods for single-cell perturbation screening, cellular barcoding, and lineage tracing; and create image-analysis pipelines for high-content and optical screens. The role also integrates functional genomics and imaging results with transcriptomics and proteomics, applies modern AI/ML approaches to target triage and evidence synthesis, and establishes standards for reproducible research and FAIR data infrastructure. The Director will collaborate with experimental scientists, software engineers, and external partners to advance shared analytical platforms and support Therapeutic Area target identification. The position is based in Cambridge, Massachusetts, with hybrid work arrangements and up to 10% travel. The posted base salary range for the primary location is $214,100–$337,000, and the successful candidate will be eligible for an annual bonus and long-term incentive, if applicable. The role has regular employee status; relocation is not offered and visa sponsorship is not available.

Requirements

Ph.D. in Bioinformatics, Biostatistics, Computational Biology, Statistics, Computer Science, Mathematics, or a related field.
At least 10 years of relevant experience in computational biology, bioinformatics, biostatistics, or a related quantitative discipline, including hands-on analysis of large-scale NGS and functional genomics datasets.
Demonstrated experience leading and building analytics teams, setting technical strategy, and mentoring scientists.
Passion for solving biological problems through computational methods, with a proactive focus on detail and execution.
Experience with computational analysis, algorithm development, and biological interpretation of diverse large-scale NGS and functional genomics datasets.
Proven track record applying machine learning to single-cell RNA sequencing data to identify novel patterns and functional insights.
Experience with experimental design of biological assays, statistical hypothesis testing, and integration of results from multiple omics data sources.
Proficiency in at least one statistical programming language, such as R or Python, and experience with version control environments such as Git.
Familiarity with public data repositories such as The Cancer Genome Atlas, Dependency Map, Cancer Cell Line Encyclopedia, and Clinical Proteomic Tumor Analysis Consortium.
Experience with AWS cloud computing infrastructure and Linux environments.
Excellent oral and written communication skills.

Nice To Haves

Strong postdoctoral or relevant industry experience, including leading multidisciplinary teams or functions and influencing scientific strategy across an organization.
Substantial computational experience with functional genomics data, including CRISPR screen hit-calling frameworks and library-design interpretation.
Experience with optical pooled CRISPR screening image-analysis pipelines and integration of morphological readouts with genomic datasets.
Expertise applying deep learning to image-based phenotypic profiling and cell classification for target identification.
Deep understanding of general disease biology and immunology, with knowledge of current functional genomics research.
Expertise using network-based analysis frameworks or transfer learning to infer gene-regulatory patterns from diverse NGS datasets.
Hands-on experience building or deploying LLM-powered systems or AI tools for biological data interrogation.
Experience developing interactive data visualization tools, such as R Shiny, for multiomics readouts.
Track record of developing novel functional genomics methods, demonstrated through first-author publications or released tools.

Responsibilities

Lead the design and development of scalable computational analytics frameworks for pooled, arrayed, single-cell, and optical CRISPR screens, including QC pipelines, library design, and longitudinal readout analysis.
Invent and scale methods for functional genomics, including single-cell perturbation screening, cellular barcoding, and lineage tracing, to elucidate adaptive resistance mechanisms and drug combinations.
Build image-analysis pipelines for high-content and optical CRISPR screens and use morphological phenotypes to inform biological understanding and target prioritization.
Integrate functional genomics and imaging results with high-throughput transcriptomics and proteomics to develop multi-evidence target-prioritization packages across stages of drug discovery.
Apply AI and machine learning, including LLM-powered agentic workflows and network-based methods, to triage targets and synthesize biological evidence.
Build, lead, and grow a team of scientists; set the strategic and technical direction for functional genomics analytics; and drive standards for reproducible research and FAIR data infrastructure.
Collaborate with experimental scientists, software engineers, and external partners to advance shared analytical platforms and support Therapeutic Area target identification.