Grad Intern - Knowledge Graph Applications (Summer 2027)

What You Will Do

During this program, you will explore how artificial intelligence, knowledge graphs, and graph analytics can be used to better understand patient journeys and address complex epidemiology and real-world evidence questions.

• Design and develop a prototype knowledge graph representing longitudinal patient journeys, including relevant relationships among patient characteristics, treatments, clinical events, and outcomes.
• Identify and apply established graph algorithms to investigate epidemiology questions that can be challenging to address using traditional tabular data structures and predictive modeling approaches.
• Explore approaches for stratifying patients based on treatment patterns and outcomes and for identifying patient subgroups with similar clinical journeys.
• Use AI-assisted tools and methods to support project development while applying appropriate human oversight, validation, and responsible AI practices.
• Evaluate additional use cases, such as identifying common treatment pathways, characterizing transitions in care, and assessing relationships among treatments, clinical events, and outcomes.
• Compare knowledge graph-based methods with selected traditional analytical approaches, documenting their relative strengths, limitations, and appropriate applications.
• Deliver reusable analytical code, technical documentation, a working prototype or demonstration, and a final presentation summarizing findings, organizational value, and recommendations for future development.

Program Eligibility Requirements

• Must be available to work a full-time schedule.
• Expected continued enrollment in an accredited college or university following the internship program / co-op.
• Student must be located in the United States for the duration of the internship program.

What We Expect of You

• Currently enrolled in a Master's or PhD program in data science, computer science, artificial intelligence, biomedical informatics, biostatistics, epidemiology, computational biology, or a related quantitative discipline.
• Experience using Python, R, or a comparable programming language for data analysis, statistical modeling, machine learning, or AI application development.
• Foundational knowledge of artificial intelligence, graph theory, knowledge graphs, network analysis, graph databases, or graph-based machine learning.
• Ability to work with complex datasets and translate scientific or business questions into analytical approaches.
• Strong problem-solving, written communication, and presentation skills.
• Ability to work independently while collaborating effectively with data scientists, epidemiologists, and other cross-functional partners.

Basic Qualifications

• 18 years or older.
• Graduated with a bachelor's degree from an accredited college or university.
• Currently enrolled in an MBA, Master's, PharmD, or PhD program from an accredited college or university and completion of the first year of the program before the internship starts.

Preferred Qualifications

• PhD or Master's thesis work focused on graph analytics, knowledge graphs, artificial intelligence, network science, real-world data, or a closely related area.
• Experience working with healthcare real-world data, such as administrative claims, electronic health records, registries, or other longitudinal patient-level datasets.
• Familiarity with graph databases, query languages, or analytical frameworks such as Neo4j, Cypher, SPARQL, PyTorch Geometric, or comparable technologies.
• Experience applying graph algorithms for community detection, clustering, similarity analysis, path analysis, link prediction, or patient stratification.
• Experience using generative AI, large language models, machine learning, or AI-assisted development tools in an analytical or research workflow.
• Understanding of epidemiology, patient journey analysis, treatment patterns, clinical outcomes, or real-world evidence research.
• Experience developing reproducible analytical workflows and communicating technical results to scientific and nontechnical audiences.