Principal Engineer Sabeti Lab

About the Broad

The Broad Institute of MIT and Harvard is a leading biomedical research institute dedicated to the bold mission of using the full power of genomics to transform the understanding and treatment of disease. The Broad Institute seeks to describe all of the molecular components of life and their connections; discover the molecular basis of major human diseases; develop effective new approaches to diagnostics and therapeutics; and disseminate discoveries tools methods and data openly to the entire scientific community.

Founded in 2004 by Eric Lander and philanthropists Eli and Edythe L. Broad the Broad Institute includes faculty professional staff and students from throughout the MIT and Harvard biomedical research communities and beyond with collaborations spanning more than a hundred private and public institutions in more than 40 countries worldwide.

About the Role

This role is part of the Sabeti Labs work as a CDCs Pathogen Genomics Center of Excellence (PGCoE) and within NIHs Human Virome Program (HVP) developing and scaling novel genomic methods to track the spread and evolution of viruses and other pathogens and characterize the largely unexplored collection of viruses and bacteriophages present in healthy humans. This role steers the technical direction for the labs computational infrastructure and represents the labs engineering work within the HVP consortium and to external collaborators and advises lab leadership on computational strategy and investment.

Key Responsibilities:

• Manage the architecture and long-term technical roadmap for scalable containerized workflows on Terra/Manifold for viral discovery classification assembly and characterization and lead their design implementation and optimization.
• Evaluate new and emerging bioinformatic tools for virome analysis and identification decide which to adopt and lead their integration into the groups codebase.
• Assist in defining the labs deployment strategy for scalability and cost-efficiency on cloud infrastructure forecasting compute and cost needs across projects.
• Serve as the labs technical representative to the HVP consortium and external collaborators; communicate regularly with the project teams to meet deadlines and adapt workflows to emerging research needs.
• Supervise and mentor junior computational trainees and employees who are performing research creating methods or utilizing our tools and identify the skills the team needs to develop.
• Serve as a subject-matter expert on evolving best practices in bioinformatics genomics compute infrastructure and AI in science and engineering and as a resource to collaborators and other Broad groups adopting them.

• Education: MSc or PhD in Computer Science Artificial Intelligence (AI) Bioinformatics Computational Biology or related field or equivalent industry experience.
• Experience: 10 years with bachelors degree 8 years with MSc 5 years with PhD
• Track record of leading or maintaining open-source bioinformatics software.

• Knowledge of software packaging and distribution (e.g. PyPI Conda).
• Familiarity with containerization (Docker) and CI/CD pipelines.
• Experience using Terra or other cloud-based platforms for large-scale genomic analysis including cost management at scale.
• Proficiency in writing WDL or Nextflow workflows and working with workflow engines like Cromwell or miniWDL on cloud platforms.
• Strong programming skills in Python and bash including hands-on experience with machine learning workflows (e.g. scikit-learn PyTorch or TensorFlow). Familiarity with training and inference on GPUs managing CUDA environments and optimizing ML performance in a high-throughput setting is highly desirable.
• Familiarity with git and collaborative software development practices.
• Proficiency in agentic coding tools practices and harnesses.

• Ability to take on ambiguous open-ended problems with minimal oversight manage tasks efficiently and collaborate with interdisciplinary teams.
• This is a hybrid position. Must have the ability to work in person at the Broad Institute at least 3 days a week.