AI/ML Automation Pipelines Intern

We are currently seeking an AI/ML Automation Pipelines Intern for Summer 2027. This position works for approximately 37.5 hours per week.

Responsibilities

The AI/ML Automation Intern will explore how AI and machine learning can streamline programming workflows in clinical trial reporting. The focus will be on building proof-of-concept automation pipelines that use Python and ML models to improve efficiency, accuracy, and standardization.

Objectives

• Learn how AI/ML can be integrated into clinical data workflows.
• Build automation pipelines to reduce manual coding and enhance prediction accuracy.
• Apply Python programming and ML frameworks (e.g., scikit-learn, LangChain) to real-world data challenges.

Key Deliverables

• Develop a prototype ML-based code recommender for TLF (Tables, Listings, Figures) generation.
• Automate study metadata extraction from protocols or SAPs using NLP models.
• Create a Python-based monitoring dashboard for QC metrics across multiple studies.
• Present findings and demonstrate automation pipeline in a showcase session.

Qualifications

Currently pursuing Masters or PhD in Biostatistics, Computer Science or relevant fields with analytics focus. Strong experience with R, R Shiny, Python and AI/ML is required.