Associate Scientist Postdoctoral Fellow - Computational Precision Genetics

Role Summary

The Precision Genetics group in the Data, AI and Genome Sciences Department seeks a Postdoctoral Research Fellow to drive computational work on a translational project developing a reusable multi-omics and AI/ML framework to discover mechanism-based companion diagnostic (CDx) biomarkers that predict treatment response in autoimmune diseases. The role combines organoid drug-profiling, multi-modal functional assays, single-cell and spatial transcriptomics, and development of interpretable AI/ML models to identify predictive biomarkers and benchmark model fidelity against clinical datasets.

Responsibilities

• Analyze multi-modal pre- and post-treatment readouts, including epithelial barrier assays, cytokine profiling, single-cell RNA-seq, and spatial transcriptomics (e.g., 10x Visium, GeoMx, Stereo-seq).
• Develop, benchmark, and maintain reproducible computational pipelines for bulk, single-cell, and spatial transcriptomics data processing (QC, alignment, cell-type annotation, and spatial analyses).
• Implement multi-omic integration strategies combining spatial transcriptomics, single-cell expression, cell composition estimates, and genotype/SNP data.
• Design, train, evaluate, and interpret AI/ML models (supervised and unsupervised) for predictive biomarker discovery and companion diagnostic candidate prioritization, emphasizing feature selection and model explainability.
• Document methods, workflows, and results thoroughly; prepare and contribute to manuscripts, conference presentations, and IP/translation activities as appropriate.
• Collaborate effectively with wet-lab scientists, clinicians, and computational colleagues, present results to the team and stakeholders.

Qualifications

• Required: Ph.D. or completion within 6 months in Computational Biology, Bioinformatics, Systems Biology, Genomics, Biomedical Engineering, Computer Science (with bioinformatics experience), or related discipline.
• Required: Demonstrated experience analyzing single-cell and/or spatial transcriptomics data processing, clustering, differential expression, spatial analysis.
• Required: Proven ability to apply advanced AI/ML to biomedical data for biomarker discovery/patient stratification, using rigorous evaluation and reproducible Python/R pipelines
• Required: Strong programming skills in Python and/or R and familiarity with relevant libraries/tools (Seurat, Scanpy, Squidpy, Bioconductor, scikit-learn, PyTorch/TensorFlow).
• Required: Strong statistical skills and experience working with high-dimensional biological data; excellent data visualization abilities.
• Required: Excellent written and oral communication skills and evidence of productivity appropriate to career stage (publications, code repositories, or preprints).
• Required: Proven ability to work collaboratively in interdisciplinary teams and manage multiple projects concurrently.
• Preferred: Hands-on experience generating single-cell or spatial transcriptomics datasets from organoid models (10x Visium, Nanostring GeoMx, MERFISH, Stereo-seq) or close collaboration with teams that generate such data.
• Preferred: Familiarity with genotype/SNP data processing and integration (GWAS summary statistics, imputation, genotype–phenotype association analyses).
• Preferred: Experience with cloud platforms (AWS) and high-performance computing (HPC) environments.
• Preferred: Prior experience in translational biomarker discovery or developing clinically oriented predictive models.

Skills

• Bioinformatics
• Computational Analysis
• Datasets
• Large Scale Data Processing
• Scientific Writing
• Single-Cell Genomics
• Wet Lab

Additional Requirements

• Travel Requirements: 10%
• VISA Sponsorship: Yes
• Hybrid Work Model: Yes (U.S. hybrid model; details to be provided)