Intern, Biometrics

The Statistical Innovation & Data Analytics (SiDA) team is advancing AI-enabled statistical and clinical data solutions to accelerate data-driven decision-making, improve operational efficiency, and strengthen regulatory readiness across clinical development programs. This role provides hands-on experience at the intersection of statistics, clinical data science, and AI engineering.

Here’s What You’ll Do

• Develop and evaluate AI/ML and agentic solutions for clinical data analysis, statistical programming, and workflow automation, including tool-calling, RAG, and skill-based agent architectures.
• Explore LLM post-training, adaptation, and evaluation approaches to improve model performance for statistical and clinical research use cases.
• Design agentic workflows with appropriate human oversight, traceability, and reproducibility for use in regulated clinical development environments.
• Build scalable and modular AI pipelines that integrate clinical, statistical, and translational datasets.
• Develop interactive data visualizations, dashboards, and analytical applications to accelerate clinical insights and decision-making.
• Collaborate with statisticians, statistical programmers, data scientists, and scientists to translate clinical and business needs into practical technical solutions.
• Explore opportunities to automate and augment the clinical data lifecycle, including data processing, analysis, QC, interpretation, and reporting.
• Contribute to documentation, evaluation, validation considerations, and reusable AI capabilities that can scale across studies and programs.

Here’s What You’ll Bring to the Table (Preferred Qualifications)

• Master, doctoral or advanced undergraduate Student in statistics, biostatistics, computational biology, health informatics, data science or computer science related quantitative disciplines.
• Excellent statistical knowledge and quantitative skills with the ability to apply the knowledge to solve scientific and clinical problems.
• Experience in coding in Python (required) and R (preferred); demonstrated ability in cloud computing platforms, containerization, backend development, and SQL.
• Experience or demonstrated interest in GenAI/LLMs, machine learning, agentic systems, model post-training, or AI application development.
• Familiarity with one or more of the following is a plus: cloud computing, containerization, APIs/backend development, RAG, model evaluation, or AI deployment.
• Experience developing data visualizations, analytical applications, dashboards, or reusable computational tools is preferred.
• Interest in building practical, reliable, and scalable AI solutions for clinical or biomedical research.
• Strong analytical thinking, engineering mindset, curiosity, and written and verbal communication skills.
• Ability to learn quickly, work across disciplines, and translate emerging AI technologies into practical solutions.