Postdoctoral Researcher in AI-Driven Data Curation and Data Integration

About the role

Location: University of Pennsylvania - Perelman School of Medicine. Open Date: Jun 02, 2026. Number of Positions: 2. Faculty Mentor: Joost Wagenaar. Department: Informatics (jointly based in the Institute for Biomedical Informatics and the Department of Biostatistics, Epidemiology, and Informatics). Open to applications from US Citizens and foreign nationals. The Wagenaar Lab conducts research at the intersection of artificial intelligence, common data elements (CDEs), and large-scale biomedical datasets, leading the academic development of the Pennsieve scientific data platform. The lab’s mission is to create scalable, sustainable infrastructure that enables data integration, reuse, and discovery across clinical and scientific research domains. This postdoctoral position will focus on developing AI-enabled methods to automate and augment data curation, emphasizing the use of CDEs to improve the usability, interoperability, and scientific value of public datasets. The successful candidate will work across disease areas—including Epilepsy, Immune Health, and programs within the NIH HEAL Initiative—to design approaches that harmonize heterogeneous datasets, enrich metadata, and support scalable data exploration. They will collaborate closely with the Pennsieve development team and a broad network of scientific collaborators to translate industry best practices in data engineering and AI into the academic research ecosystem. A central goal is to move beyond manual, project‑specific curation toward reproducible, automated, and extensible curation workflows applicable across datasets, programs, and institutions. In addition to platform and method development, the postdoctoral researcher is expected to contribute to peer‑reviewed publications, open‑source software, and community‑facing resources that advance AI‑enabled data stewardship and reuse.

Responsibilities

• Develop AI-based methods and deploy them at scale to automate and augment data curation using Common Data Elements
• Design workflows to harmonize, validate, and enrich public datasets across Epilepsy, Immune Health, and NIH HEAL programs
• Develop novel mechanisms to interrogate, visualize and interact with complex scientific datasets and increase the value of these datasets for the scientific community
• Integrate curation methods into scalable, cloud-based scientific data platforms
• Collaborate with the Pennsieve development team and scientific partners to align methods with real research workflows
• Evaluate and validate curation approaches using large, heterogeneous public datasets
• Prepare manuscripts, technical documentation, and presentations describing methods and outcomes

Qualifications

• Ph.D. (preferred) or Master’s degree in Biomedical Informatics, Computer Science, Data Science, Bioinformatics, or a related field
• Experience with machine learning, natural language processing, or AI applied to structured and unstructured data
• Familiarity with Common Data Elements, data standards, or ontology-based data representation (preferred)
• Strong programming skills in Docker, Python, Go, Java, or related languages
• Experience working with large-scale biomedical or clinical datasets
• Experience with cloud-based data processing and scalable analytics environments (AWS preferred)
• Strong written and verbal communication skills and an interest in interdisciplinary collaboration