Microbial Genomics Data Scientist

Lawrence Berkeley National Laboratory•Berkeley, CA
•$119,712 - $149,616•Hybrid

About The Position

Berkeley Lab’s Joint Genome Institute (JGI) seeks a Microbial Genomics Data Scientist to analyze single-cell and enrichment genomic datasets, characterizing microbial associations, genome evolution, and metabolic capabilities, particularly in microeukaryotes and their associated bacteria, archaea, and viruses. The position combines microbial genomics, statistics, and AI/ML to predict microbial lifestyles and metabolic dependencies, supporting cultivation and phenotyping studies in collaboration with experimental scientists. The role includes developing AI-ready functional evidence resources and validating analytical and agentic AI workflows through the JGI Data Lakehouse. The scientist is expected to execute projects independently and exercise sound methodological judgment. Deliverables include reliable software, reproducible analyses, biological insights, and reusable tools for JGI users. The position is a full-time career appointment and is eligible for a hybrid work schedule, combining telework with onsite work at Lawrence Berkeley National Lab in Berkeley, California. Hybrid employees must reside within 150 miles of the Lab. The anticipated start date is December 14, 2026. The position is open only to current Berkeley Lab staff and former employees eligible for rehire.

Requirements

  • Bachelor’s degree or equivalent knowledge/training in Bioinformatics, Computational Biology, Computer Science, Data Science, Microbiology, or a related field, and at least 5 years of experience developing and applying computational analyses to large genomic or metagenomic datasets, including biological interpretation of results, or an equivalent combination of education and experience.
  • Experience developing, evaluating, and applying statistical or machine learning methods to biological questions and implementing reproducible analytical software or workflows.
  • Proficiency in genome-resolved analyses, including assembly or binning, quality assessment, functional annotation, comparative genomics, and phylogenetic inference.
  • Strong understanding of microbial genome evolution, functional genomics, symbiosis, and metabolism, with the ability to interpret evidence for microbial associations and dependencies.
  • Knowledge of statistical and AI/ML prediction methods, model evaluation, uncertainty assessment, data leakage prevention, and independent validation.
  • Proficiency in Python or another scientific programming language, UNIX/Linux environments, and high-performance computing for large biological datasets.
  • Experience independently managing day-to-day technical work, selecting appropriate analytical methods, resolving data or workflow problems, and collaborating with scientists or technical teams.
  • Excellent oral and written communication skills, including the ability to communicate methods, results, and limitations to technical and non-technical audiences.
  • Demonstrated interpersonal skills and ability to collaborate effectively across interdisciplinary teams.

Nice To Haves

  • Ph.D. in Bioinformatics, Computational Biology, Computer Science, Data Science, Microbiology, or a related field.
  • Experience with single-cell or enrichment genomics, uncultivated microeukaryotes, microbial symbioses, or syntrophic partnerships.
  • Experience inferring metabolic capabilities or dependencies from incomplete genomes and integrating genomic evidence with phenotypic or experimental observations.
  • Experience applying biological foundation models, representation learning, or agentic and co-scientist workflows to biological data analysis.
  • Experience with API-based data access, data lakehouse or comparable infrastructure, workflow automation, or integration of multiple omics data types.
  • Experience collaborating on cultivation, phenotyping, or functional characterization studies, or developing scientific software documentation and user training.

Responsibilities

  • Collaborate with JGI scientists, users, and technical teams to define analytical questions, data needs, project objectives, and deliverables.
  • Develop and maintain software and automated pipelines to acquire, clean, integrate, standardize, and quality-check genomic datasets and metadata.
  • Build reproducible workflows for genome reconstruction, quality assessment, annotation, comparative genomics, and phylogenomics of single-cell and enrichment datasets.
  • Analyze genome evolution, gene gain and loss, horizontal gene transfer, and metabolic complementarity to identify microbial associations.
  • Develop and apply statistical and AI/ML methods to predict microbial lifestyles, metabolic dependencies, auxotrophies, and functional capabilities.
  • Validate computational predictions using curated evidence, independent datasets, and experimental observations; assess uncertainty, bias, and data limitations.
  • Contribute curated datasets and analyses to AI-ready functional evidence resources that support protein annotation and discovery of novel metabolic pathways.
  • Develop documented, version-controlled notebooks and reusable workflows through the JGI Data Lakehouse, improving reliability and computational performance.
  • Evaluate and benchmark AI agents and co-scientist tools for microbial data analysis and hypothesis generation, assessing accuracy, limitations, and reproducibility.
  • Interpret findings with experimental collaborators to prioritize organisms, microbial partnerships, and hypotheses for cultivation and phenotyping.
  • Communicate methods and results through documentation, visualizations, presentations, publications, and user training; provide technical guidance on validated workflows.

Benefits

  • Exceptional health and retirement benefits, including pension or 401K-style plans.
  • Vacation and sick time accrual.
  • Annual Winter Holiday Shutdown.
  • Parental bonding leave for mothers and fathers.
  • Pet insurance.
© 2026 Teal Labs, Inc
Privacy PolicyTerms of Service