AI-Driven Single-Cell & Spatial Omics: NIH-Funded Postdoctoral Positions

AI-Driven Single-Cell & Spatial Omics: NIH-Funded Postdoctoral Positions

University of Pittsburgh

Date Posted: Posted on 1 January 2026

Location: United States (US)

Job Tags:

ai machine learning, bioinformatics, spatial multi-omics, spatial proteomics

The Osmanbeyoglu Lab at the University of Pittsburgh School of Medicine is recruiting NIH-funded postdoctoral researchers with strong backgrounds in machine learning and artificial intelligence to join a growing, interdisciplinary research program at the interface of ML, single-cell and spatial omics, and systems biology.

Postdoctoral fellows will develop novel machine learning and deep learning methods—including graph neural networks, attention-based models, multimodal learning, and interpretable AI—to analyze large-scale single-cell and spatial transcriptomics datasets. The scientific focus is on inferring context-specific regulatory programs that drive cancer progression and end-stage disease, directly linking methodological innovation to biological and clinical insight.

Research emphasizes rigorous algorithmic development, interpretability, and benchmarking on real, noisy, high-dimensional data, not toy problems. Projects span method development and biological discovery and are carried out in close collaboration with experimental biologists, pathologists, and clinicians, providing unique opportunities to work on clinically meaningful datasets with translational relevance.

The lab offers a supportive, intellectually rigorous environment for candidates seeking scientific independence, strong mentorship, and high-impact publications. We value clean code, reproducible research, thoughtful model design, and collaborative science, and we are deeply committed to the career development and long-term success of our trainees.

Qualifications

Ph.D. in machine learning, AI, data science, computer science, or a related quantitative field

Strong programming skills in Python (experience with PyTorch, TensorFlow, or JAX preferred); R a plus

Experience with deep learning architectures (e.g., GNNs, representation learning, attention models)

Comfort working in Linux/HPC environments and with large-scale datasets

Interest in applying ML to scientific problems; prior experience with biological data is not required

Strong communication skills and ability to work across disciplines

Career Outcomes

Postdoctoral fellows are well positioned for tenure-track faculty positions in ML, biomedical informatics, or computational biology, as well as research scientist roles in industry (applied AI, healthcare AI, life sciences). Training emphasizes methodological originality, end-to-end project ownership, high-impact publications, grant writing, and mentoring, providing strong signals for both academic and industry career paths.