Clinical Development Data Science Intern

Job Overview

The Clinical Development Data Science Intern will join Genmab's Clinical Development Data Science team and contribute to innovative AI/ML initiatives across the clinical development lifecycle. This role is ideal for a highly technical, impact-driven data scientist who is pursuing a Ph.D. in a quantitative or computational discipline, and who is excited to apply modern machine learning, natural language processing, and generative AI to real clinical and scientific challenges in oncology.

The intern will support projects such as building AI-powered tools to assist trial design, developing analytics pipelines for clinical and safety data, and prototyping advanced models that help clinicians and scientists make better, faster decisions.

What You'll Do

• Develop machine learning and NLP pipelines to extract, organize, and summarize information from clinical trial protocols, regulatory documents, and unstructured biomedical text.
• Support the development of AI-driven tools that accelerate protocol design through information retrieval, extraction, and summarization.
• Enhance pharmacovigilance and safety monitoring through automated literature surveillance, risk modeling, anomaly detection, and severity prediction.
• Enable portfolio planning and decision-making through predictive modeling of key milestones and drivers.
• Support regulatory intelligence and affairs through analysis and synthesis of documents, precedents, and health authority decisions.
• Apply advanced modeling techniques including transformers, generative models, survival analysis, clustering, and other ML approaches.
• Experiment with explainability methods (e.g., SHAP, LIME) to improve the interpretability of models used in clinical decision-support contexts.
• Contribute to documentation, model evaluation, technical reviews, and final presentations to internal stakeholders.

Required Qualifications, Capabilities And Skills

• Sustained progress in a Ph.D. program in a quantitative or computational discipline (Computer Science, Data Science, Statistics, Physics, Computational Chemistry, Computational Biology, Applied Mathematics, Engineering, or related quantitative/technical field).
• Master's students with strong applied experience may also be considered.
• Strong proficiency in modern Python for machine learning and scientific computing (e.g., PyTorch/TensorFlow, scikit-learn, spaCy, Hugging Face transformers, pandas, NumPy).
• Candidates should be experienced in building modular scripts and reusable modules, command-line utilities, and structured codebases for data processing and machine learning workflows.
• Experience applying ML or NLP methods to real-world datasets.
• Ability to design, build, and evaluate computational models end-to-end.
• Excellent analytical problem-solving abilities and intellectual curiosity.
• Clear written and verbal communication skills.
• High attention to detail, scientific rigor, and commitment to producing high-quality work.
• Ability to work independently as well as collaboratively within interdisciplinary teams.

Preferred Qualifications, Capabilities And Skills

• Experience with large language models (LLM), retrieval-augmented generation (RAG), or generative AI workflows.
• Prior work involving unstructured document parsing (e.g., PDFs, scanned text, scientific literature).
• Full-stack data science skill set, including experience with writing production-quality, modular, and reusable Python code.
• Building scalable, reproducible systems and packaging code for broader use.
• Containerization (e.g., Docker) and reproducible compute environments.
• Workflow or pipeline orchestration tools (Airflow, Prefect, Dagster, etc.).
• Cloud computing environments (AWS, Azure, GCP).
• Experience using Git repositories and version-control workflows, including branching strategies, pull requests, peer code reviews.
• Good commit hygiene and collaborative development practices.
• Familiarity with GitHub, GitLab, or similar platforms.
• Exposure to CI/CD, structured logging, automated testing, or other professional engineering practices.
• Experience with MLOps concepts such as model packaging, monitoring, reproducibility, and deployment is a strong plus.

General Intern Information – Date/Location/Schedule

Internships will take place over 10 weeks from June – August 2027. This role will be based in Princeton, NJ and operate on a required hybrid schedule – 3 days in the office and 2 days remote per week. This role is not eligible for work visa sponsorship at the time of the application or in the future.