SI/ML Computational Biologist - Postdoctoral Researcher

LLNL•Livermore, CA

5d•Onsite

About The Position

Lawrence Livermore National Laboratory is seeking a Postdoctoral Research Staff Member to conduct research at the intersection of super intelligence (SI), machine learning (ML), and computational biology. The role applies and adapts state-of-the-art SI/ML approaches to study host-response dynamics in complex biological systems. Research integrates large-scale multiomic datasets—including bulk, single-cell, spatial, and multimodal data from animal models and human cohorts—to identify molecular programs associated with disease progression, immune responses, and biological resilience. The researcher will use modern methods such as deep learning, self-supervised learning, and biological foundation models to derive biologically meaningful insights and develop predictive models that generalize across biological systems. The position is in the Integrative Multi-Omics Group and involves working under senior scientists’ guidance on high-dimensional biological data at scale in a collaborative, multidisciplinary environment. This is a temporary, mentored postdoctoral appointment for an initial two-year term, with the possibility of extension to a maximum of three years. Applicants must have received their Ph.D. or equivalent doctorate within five years of the anticipated start date.

Requirements

Must be eligible to access the Laboratory in compliance with Section 3112 of the National Defense Authorization Act (NDAA).
Ph.D. in Computational Biology, Bioinformatics, Computer Science, Statistics, Data Science, or a related field.
Strong background in machine learning, statistical modeling, computational biology, or a related quantitative discipline.
Experience analyzing high-dimensional biological data such as genomics, transcriptomics, or related modalities.
Proficiency in Python and R.
Experience with ML frameworks such as PyTorch, TensorFlow, or similar.
Familiarity with Linux/Unix and scientific computing workflows.
Demonstrated ability to conduct high-quality research and publish results in peer-reviewed journals.
Demonstrated ability to work effectively in a collaborative research environment.
Strong written and verbal communication skills.
Must have received a Ph.D. or equivalent doctorate within five years of the anticipated start date.

Nice To Haves

Experience with deep learning or probabilistic modeling approaches, such as variational autoencoders, scVI, or related methods.
Experience with single-cell, spatial, and/or multimodal omics data.
Experience with multiomic data integration, including multimodal single-cell datasets.
Experience with transfer learning, domain adaptation, cross-dataset integration, or batch correction.
Experience with transformers, self-supervised learning, or pretrained models for biological data.
Experience training and scaling machine learning models on large datasets.
Interest in immunology, host-pathogen biology, or disease modeling.

Responsibilities

Develop and apply machine learning methods for prediction and representation learning from high-dimensional biological data.
Contribute to the design and implementation of workflows for integrative analysis of bulk, single-cell, spatial, and multimodal multiomic datasets.
Investigate, develop, and apply approaches for multimodal data fusion, cross-dataset integration, and transfer learning.
Train, adapt, and evaluate self-supervised and foundation models for omics data.
Develop and apply interpretable models linking molecular states to disease trajectories and host-response phenotypes.
Process and analyze large-scale sequencing and other omics datasets.
Present research findings at seminars, conferences, and technical meetings.
Contribute to research design and project execution.
Collaborate in a multidisciplinary team environment.
Publish results in peer-reviewed journals.
Perform other duties as assigned.