Director, Data Science

Omega Therapeutics is a Clinical-stage biotechnology company pioneering the first systematic approach to use mRNA therapeutics as a new class of programmable epigenetic medicines by leveraging its OMEGA Epigenomic Programming™ platform. The OMEGA™ platform harnesses the power of epigenetics, the mechanism that controls gene expression and every aspect of an organism's life from cell genesis, growth and differentiation to cell death. Using a suite of technologies, paired with Omega’s process of systemic, rational and integrative drug design, the OMEGA platform enables control of fundamental epigenetic processes to correct the root cause of disease by returning aberrant gene expression to a normal range without altering native nucleic acid sequences. Omega’s engineered, modular, and programmable mRNA-encoded epigenetic medicines, Omega Epigenomic Controllers™, target specific intervention points amongst the thousands of mapped and validated proprietary and novel DNA-sequence-based epigenomic loci, EpiZips™ to durably tune single or multiple genes to treat and cure disease through Precision Genomic Control™. Omega is currently advancing a broad pipeline of development candidates spanning a range of disease areas, including oncology, regenerative medicine, multigenic diseases including immunology, and select monogenic diseases.

About the Role:

Omega Therapeutics, Inc. is seeking a Director of Data Science to lead Omega's computational biology, machine learning, and scientific data platform efforts across the R&D organization.  Working within a highly integrated Genomics, Data Science, and Therapeutics Discovery department, the successful candidate will champion quantitative assessment and interpretation of non-clinical data (Platform, Discovery, Translational, TechOps, etc.), lead novel algorithmic platform growth, and contribute to experimental designs for program and platform data generation.  Essential skills include excellent communication across diverse biological/technical backgrounds, an expertise in functional genomics data analysis and novel ML model development, and the ability to drive hypothesis-driven research goals through multidimensional omics datasets.  We are looking for an enthusiastic, detail oriented and highly motivated individual with a passion for bringing novel medicines to patients and is comfortable working in a fast-paced scientific team.

Key Responsibilities:

• Serve as point/liaison across Program and Platform efforts to identify key questions addressable via genomic/high-throughput assays, partner in experimental design, and manage execution of targeted computational analysis plans
• Drive expansion and creation of novel ML approaches - fit-for-purpose to advance core Platform capabilities (omics, therapeutics design, etc.), and accelerate drug development
• Manage and grow cloud-based scientific data platform, incorporating diverse data types and technologies for insights within and between studies, leading to accelerated, data-driven decision making
• Identify and evaluate novel computational methodologies and partnerships that leverage emerging technologies in an opportunistic manner
• Effectively identify and communicate opportunities for contributions by Data Science to stakeholders at all levels, elucidating key messages for decision-making

Required Skills:

• Management of, or experience within both a computational biology function and biological ML modeling team, with the ability to bridge disciplines across teammates and advocate common goals
• Experience solving large-scale, real-world scientific problems within cross-functional, multi-disciplinary teams
• Extensive experience with diverse functional genomic & epigenetic assay types (both bulk/single-cell), eg RNA-seq, ChIP-seq, ATAC-seq, Cut&Run, WGMS, Hi-C, SLAM-seq, etc. - as well as systems biological and network analysis approaches
• Deep understanding of modern ML approaches (Graph Neural Networks, Transformers, etc.) and their application to high-throughput/molecular biological data.
• Understanding or experience with precision medicine technologies (eg CRISPR, editing, etc.) and the application of computational analyses for interrogation
• Fluency in R, python, AWS stacks, and other HPC environments
• Prior exposure to epigenetics, genetics data, GWAS, eQTLs, preferred
• Highly adaptable and responsive to technical and business opportunities – comfortable delivering against challenging project needs and timelines

Required Qualifications:

• PhD in Computer Science, Machine Learning, Computational Biology, Systems Biology, or related disciplines, with 5+ years of industry experience
• Recognized excellence working in multidisciplinary teams as evidenced from peer-reviewed publications and strong references