"Data Scientist"

Job Description Summary

The Data Scientist will lead and support advanced computational biology and biomedical informatics research, working in close partnership with principal investigators and collaborators. A primary focus will be integrating and analyzing large-scale clinical, genomics, proteomics, imaging, and informatics data, with the Penn Medicine Biobank (PMBB) as a central resource.

The Data Scientist will assess project feasibility, contribute to study design, and oversee analytic execution. They will develop and maintain computational pipelines, ensure methodological rigor and reproducibility, and mentor trainees and staff in computational approaches. Additional responsibilities include contributing to manuscripts, grant applications, and presentations at scientific meetings.

This is a leadership opportunity at the intersection of data science and biomedical research, enabling high-impact discoveries and building shared infrastructure that accelerates future studies.

Job Responsibilities

• Lead the design, development, and execution of computational genomics, multi-omics integration, and biomedical informatics projects in collaboration with the principal investigators.
• Collaborate with PIs and PMBB Clinical Informatics and Genomics Core on projects that leverage imaging-derived phenotypes, including working with AI and deep learning methods to extract features from medical images and integrating these into downstream analyses.
• Develop and maintain computational pipelines for phenotype generation, data harmonization, and integration across clinical, imaging, and genomic datasets.
• Assess feasibility, efficiency, and study design for proposed projects, providing input on timelines and resource planning.
• Oversee data analysis workflows to ensure methodological rigor, reproducibility, and scalability.
• Apply statistical genetics and bioinformatics methods to conduct biobank-scale analyses.
• Contribute to manuscripts, grant applications, and conference presentations.
• Mentor and guide trainees, staff, and junior investigators in computational methods and study design.
• Provide computational expertise and support to collaborators, including phenotype generation and downstream analysis.
• Coordinate with other cores and research groups to build shared infrastructure and tools that expand the impact of PMBB and related resources.
• Act as a liaison between the PI's groups, institutional cores, and external partners to strengthen collaborative research.

Qualifications

Master of Science and 1 to 2 years of experience, or an equivalent combination of education and experience. PhD in Computational Biology, Bioinformatics, Statistical Genetics, Computer Science, or a related field strongly preferred.

Strong record of research in statistical genetics or large-scale omics analysis.

Experience with machine learning or deep learning applications in biomedical research.

Strong publication record in data science, computational biology or related fields.

Proficiency in Python, R, or comparable programming languages; experience with HPC or cloud-based environments.

Excellent communication skills and experience working in cross-disciplinary collaborations.

Resume and cover letter required with application.