Postdoctoral Fellow (NIEHS)

This fellowship will focus on developing causal AI and computational methods for analyzing single-cell perturbation and multi-omics data in order to investigate disease mechanisms and advance precision medicine.

Prospective candidates will develop and apply advanced computational, statistical, and AI/ML methods to analyze large-scale perturbation datasets generated using CRISPR-based functional genomics technologies, including Perturb-seq, CRISPRi, CRISPR knockout, pooled genetic screens, and pharmacological and/or environmental perturbation experiments.

Research will further focus on developing interpretable causal inference methods to reconstruct gene regulatory networks, signaling pathways, and cellular state transitions from single-cell perturbation data using probabilistic graphical models, mechanistic systems biology models, causal discovery algorithms, graph neural networks, and perturbation-based frameworks such as Nested Effects Models (NEMs).

These methods will be evaluated and applied using large-scale multimodal datasets that integrate genomic, transcriptomic, epigenomic, proteomic, metabolomic, single-cell, and spatial molecular profiling data together with public reference resources, including the Human Cell Atlas, and other national and international consortium datasets.

Current projects include characterizing spatial molecular responses following ischemic kidney injury and investigating how genetic variation and environmental exposures influence cellular responses, immune dynamics, and disease susceptibility across diverse biological systems.

Prospective candidates should have completed, or be close to completing, a Ph.D. in bioinformatics, computational biology, biostatistics, statistics, computer science, systems biology, genetics, applied mathematics, machine learning, artificial intelligence, biomedical engineering, and/or a closely related quantitative life science discipline.

Applicants with backgrounds in causal AI, graph machine learning, probabilistic graphical models, reinforcement learning for biology, or computational network biology are strongly encouraged to apply.

Applicants should have strong programming skills and experience working with large-scale biological datasets, proficiency in R, Python, MATLAB, Linux/Unix, Shell scripting, and/or Java, and a strong background in statistical learning, machine learning, computational biology, or systems biology. Experience analyzing next-generation sequencing datasets, including bulk and/or single-cell genomics data, is welcome, as is familiarity with statistical modeling, probabilistic methods, or network analysis.

Experience with single-cell RNA sequencing, Perturb-seq, CRISPR screening, functional genomics, and/or spatial omics technologies is a plus. Excellent written and verbal communication skills in English are essential.

U.S. citizens and permanent residents are eligible to apply. NIH welcomes foreign nationals with the exception of individuals from this list.