SI/ML Computational Biologist

About the Role

This is a one-year Academic Graduate Appointee position with the possibility of extension to a maximum of two years. The role is within the Integrative Multi-Omics Group of the Biosciences and Biotechnology Division and requires full-time on-site presence.

Key Responsibilities

• Collaborate with experimental scientists, computational biologists, computer scientists, and engineers on defined computational and data-analysis assignments under guidance from senior staff.
• Process and analyze bulk transcriptomic, single-cell, and spatial transcriptomic data from animal models and human cohorts using established bioinformatics methods.
• Assist with workflows for multimodal data integration.
• Assist with implementing, testing, and applying established machine-learning methods, including interpretable models, for prediction and representation learning from high-dimensional biological data, under guidance, linking molecular states to disease trajectories and host-response phenotypes.
• Support the training, adaptation, and evaluation of self-supervised and foundation models for biological applications.
• Document code and analyses to support reproducibility.
• Contribute to technical reports, presentations, and potentially peer-reviewed publications.
• Present research progress and technical results to internal teams, collaborators, and other scientific audiences with guidance from senior staff.
• Meet project deadlines and maintain high-quality deliverables.
• Perform other duties as assigned.

Requirements & Tech Stack

• Ability to secure and maintain a U.S. Department of Energy Q-level security clearance, which requires U.S. citizenship and a federal background investigation.
• Bachelor’s or Master’s degree in computer science, data science, bioinformatics, computational biology, statistics, or a related field.
• Coursework, research, internship, or project experience analyzing high-dimensional biological data (e.g., genomics, transcriptomics) using standard bioinformatics pipelines and statistical methods.
• Foundation in machine learning and statistical modeling demonstrated through coursework, research, or technical projects.
• Proficiency in Python and/or R.
• Proficiency in Linux/Unix, including command-line tools and shell scripting.
• Strong written and verbal communication skills.
• Ability to work effectively in a collaborative research environment.

Qualifications We Desire

• Exposure to or experience applying machine learning or deep learning methods to biological data, including single-cell, spatial, or multimodal omics.
• Experience running large-scale workflows on GPU or high-performance computing (HPC) systems.
• Familiarity with multiomic data integration, transfer learning, or foundation models for biological data.
• Experience with version control (Git) and workflow managers (e.g., Nextflow or Snakemake).
• Interest in immunology, host-pathogen biology, or disease modeling.
• Relevant research experience, publications, internships, or substantial technical projects.