Post Doctoral.Associate

We are seeking a highly motivated and productive postdoctoral researcher to contribute to federally funded projects in machine learning, regulatory genomics, single-cell multi-omics, spatial transcriptomics, and precision oncology. The successful candidate will apply and develop computational methods, take ownership of research projects, and advance them toward reproducible software, scientific deliverables, and peer-reviewed publications.

Key Responsibilities

• Lead computational projects from study design and data processing through modeling, validation, biological interpretation, and publication.

• Analyze large-scale bulk, single-cell, multi-omic, and spatial datasets.

• Develop and evaluate machine-learning methods for classification, prediction, multimodal integration, and regulatory inference.

• Apply rigorous validation practices, including appropriate data partitioning, cross-validation, baseline comparisons, external validation, and assessment of bias and generalizability.

• Develop reproducible, well-documented, version-controlled, and open-source software.

• Prepare publication-quality figures, manuscripts, presentations, and grant reports.

• Collaborate effectively with computational, experimental, and clinical investigators.

• Provide regular, structured progress updates and communicate challenges, absences, or anticipated delays promptly.

• Meet agreed-upon milestones and deadlines, respond constructively to feedback, and complete revisions and action items.

• Support the mentorship of junior researchers, as appropriate.

Required Qualifications

• PhD in computational biology, bioinformatics, biostatistics, statistics, mathematics, computer science, or a related quantitative field.

• Strong programming skills in Python and/or R.

• Demonstrated expertise in machine learning, statistics, omics data analysis, or computational biology.

• Understanding of model selection, regularization, overfitting, data leakage, class imbalance, performance evaluation, and generalization.

• Ability to translate broad research objectives into specific analyses, timelines, and deliverables with limited supervision.

• Demonstrated ability to independently plan, implement, troubleshoot, and complete computational research projects.

• Evidence of completing projects through peer-reviewed publications, software releases, or other substantive research outputs.

• Ability to critically evaluate and justify analytical decisions rather than relying uncritically on existing pipelines or AI-generated outputs.

• Strong scientific writing, communication, collaboration, and project-management skills.

• Demonstrated reliability, accountability, responsiveness to feedback, and ability to follow projects through to completion.

Preferred Qualifications

• Experience with single-cell, multi-omic, spatial transcriptomic, proteomic, or cancer genomic data.

• Experience with deep learning, graph neural networks, attention-based models, multimodal learning, or regulatory network inference.

• Familiarity with PyTorch or TensorFlow, high-performance computing, and reproducible workflow development.

• A record of leading computational projects or first-author manuscripts from analysis through publication.

Research Integrity and Data Responsibility

The successful candidate must maintain accurate and reproducible research records; protect confidential, controlled-access, and human-subject data; report findings, uncertainty, and limitations transparently; and follow institutional requirements for research ethics, authorship, data provenance, responsible AI use, and responsible conduct of research.

The University of Pittsburgh is an Equal Opportunity Employer.

N/A

The University of Pittsburgh is an equal opportunity employer / disability / veteran.

PI287268504