Computational Data Scientist II

The Bioinformatics Core within the Division of Health Informatics at UPMC Children's Hospital of Pittsburgh is seeking a computational biologist or data scientist to develop and apply machine learning and deep learning methods for omics-driven biomedical research. This individual will work closely with faculty and collaborators across multiple pediatric research programs to support biologically grounded, translationally relevant research. Equivalent relevant work experience may be substituted for degree requirement.

This position is located at UPMC Children's Hospital of Pittsburgh in Lawrenceville. PA Child Abuse History Clearance, PA State Police Criminal Record Check, and FBI Criminal Record Check will be required prior to the start of employment. Also, a current TB test will be required as a condition of employment. EEO/AA/M/F/Vets/Disabled.

Minimum Qualifications

Applicants should have an MS or PhD in computational biology, bioinformatics, computer science, statistics, data science, biomedical informatics, or a related quantitative field.

The successful candidate should have strong programming skills in Python and/or R, with experience using libraries such as PyTorch, Tensor Flow, scikit-learn, or comparable tools. Experience in applying computational or statistical modeling to biomedical or biological datasets is expected.

Prior experience working with single-cell, spatial omics, or related high-dimensional omics datasets is highly desirable. Candidates should be strong critical thinkers who can translate ideas into completed analyses, models, or tools; manage contributions across multiple collaborative research projects; work independently and as part of multidisciplinary teams; and demonstrate strong oral and written communication skills.

Preferred qualifications include:
Demonstrated experience designing and implementing models for high-dimensional biological data, beyond routine application of existing analysis pipelines.
Hands-on experience with graph neural networks or perturbation modeling.
Experience integrating omics data with clinical data sources such as electronic health records (EHR).
Evidence of independent technical contribution, such as first-author or co-author publications, preprints, conference presentations, open-source software, deployed tools, analytical pipelines, or a relevant project portfolio.