Microbiome Data Scientist Jobs (NOW HIRING)

About the Opportunity

The Roux Institute at Northeastern University (NU) and the Jackson Laboratory (JAX) are seeking two 'co-mentored' postdoctoral fellows as part of the JAX/Roux Institute joint Applied Data Science Postdoctoral Fellowship program. Under this program, postdoctoral trainees will be co-mentored by NU and JAX researchers working on priorities identified by both organizations. Projects under this program are jointly selected to enhance the JAX/Roux partnership, align with each institution's strategic priorities, and integrate biological and data science. This cycle's focus is on AI-powered data analysis to advance hypothesis-driven research related to addiction.

Computational analysis of previously collected data can increase the speed and efficiency of life sciences research. Developing the algorithms, infrastructure, and governance necessary for such analysis can simultaneously enhance hypothesis generation, computational modeling, and post hoc support for laboratory studies and provide the substrate necessary for artificial intelligence (AI) guided experimental design and optimization of scarce/costly resources, such as animal models. As AI capabilities advance, the computational, infrastructure, and governance challenges associated with computational data analysis will grow rapidly.

The positions will be located at The Roux Institute at Northeastern University, in Portland, Maine, where JAX has co-located its data science team. The position will be supervised by research faculty or research staff and work will be conducted with experimental researchers who are collaborating partners of the Roux Institute and will thus include opportunities for collaboration with other faculty at the Roux Institute and other colleges at Northeastern University.

The postdoc will contribute to and help lead projects that may involve concepts and priorities such as knowledge-graph-driven data integration, AI-powered literature review, agentic database search assistants, multi-omics analysis tools, life sciences foundation models, and "AI scientists."

PROJECT 1. Postdoctoral Research Project: Explainable AI for Gut Microbiome-Host Interactions in Cocaine Use Disorder

Cocaine use disorder (CUD) remains a major public health challenge with no approved pharmacological treatments or predictive biomarkers. Emerging evidence suggests that the gut microbiome plays a significant role in addiction-related behaviors by influencing brain function, immune signaling, and metabolite production. This project seeks to uncover the biological mechanisms linking the gut microbiome, host genetics, and addiction vulnerability.

The postdoctoral fellow will lead the development of cutting-edge, explainable graph neural network (GNN) models that integrate microbiome functional profiles, host genetic variation, and behavioral phenotypes from one of the world's largest mouse systems genetics resources. These models will leverage over a decade of data generated through the Center for Systems Neurogenetics of Addiction (CSNA), together with additional datasets from ongoing NIH-funded studies at The Jackson Laboratory.

A major focus of the project is cross-species translation. Using publicly available human genetic, microbiome, and multi-omic datasets, the fellow will identify conserved biological pathways and microbiome-derived metabolites that contribute to addiction vulnerability in both mice and humans. The ultimate goal is to discover novel biomarkers and therapeutic targets that can guide future clinical interventions for substance use disorders.

PROJECT 2. Distinct Temporal Architectures of Spontaneous versus Precipitated Opioid Withdrawal: Self-Exciting Point-Process Models of Continuous Home-Cage Behavior Across Genetically Diverse Mice.

The project encompasses building behavior based indices of opioid withdrawal with the goal of understanding mechanism and therapeutic platform. We hypothesize that both spontaneous and precipitated opioid withdrawal are self-exciting (branching factor > 0), that spontaneous and precipitated withdrawal have DISTINCT temporal architectures, and self-excitation indexes withdrawal severity (including anxiety-like, negative-affect-proxy behaviors) better than rate-based scores. We further hypothesize that these properties covary with genotype.

This project aims to (1) assess and understand the potential structure of withdrawal, (2) acquire data from genetically diverse mice under a multitude of conditions, and (3) develop multimodal machine learning models and methods to determine signatures and biomarkers to understand mechanisms distinguishing spontaneous versus precipitated withdrawal episodes. The spontaneous vs precipitated withdrawal distinction has clinical significance, and this project aims to detect this separation through model architecture in probabilistic temporal event dynamics.

Required Qualifications:

- PhD in computer science, engineering, biomedical data science, informatics with advantage for experience in conducting research on healthcare data.

- Experience in Artificial Intelligence (AI), Machine Learning (ML), Deep Learning (DL) particularly in Natural Language Processing (NLP) and Computer Vision (CV)

- strong record of publications

- Excellent communication skills and ability to work in a fast-paced and innovative setting

Preferred Qualifications (Project 1):

Applicants should hold a Ph.D. in computational biology, bioinformatics, genetics, neuroscience, data science, or a related discipline and have experience in machine learning, multi-omic data analysis, microbiome research, and/or systems genetics.

Position Type

Additional Information

Northeastern University considers factors such as candidate work experience, education and skills when extending an offer.

All qualified applicants are encouraged to apply and will receive consideration for employment without regard to race, religion, color, national origin, age, sex, sexual orientation, disability status, or any other characteristic protected by applicable law.

Compensation Grade/Pay Type:

Expected Hiring Range:

With the pay range(s) shown above, the starting salary will depend on several factors, which may include your education, experience, location, knowledge and expertise, and skills as well as a pay comparison to similarly-situated employees already in the role. Salary ranges are reviewed regularly and are subject to change.