Post Doctoral Fellowship: Global Patient Safety

Role Summary

Post Doctoral Fellowship: Global Patient Safety. Ambitious post-doctoral scientist with strong research and communication skills to contribute to the advancement of machine learning–based approaches for identifying risk factors associated with key safety topics. Initial focus on neuroscience, with methodology extended to other critical events and therapeutic areas. Supports activities of the Global Patient Safety Medical organization and collaborates across multiple functions to strengthen safety data analysis.

Responsibilities

• Develop and validate ML models to predict safety outcomes, identifying risk factors from patient histories, concomitant medications, imaging, and other clinical parameters; apply ensemble methods, resampling, cost-sensitive learning, and anomaly detection for rare event prediction.
• Present findings at conferences and publish in high-impact peer-reviewed journals.
• Understand and contribute to safety surveillance processes; propose enhancements to routine medical surveillance and integration of new methodologies into safety data analysis platforms.
• Collaborate with internal partners and external stakeholders; assist in issue management and responses to regulatory requests; share methodologies with Advanced Intelligence and other groups.
• Demonstrate knowledge of global regulatory requirements; contribute to safety quality system documents and training tools; provide medical support to GPS safety teams; understand EU QPPV roles; support audit readiness.

Qualifications

• Required: An advanced analytical, statistical, bioinformatics, or medical-related graduate degree (Ph.D., PharmD).
• Preferred: Experience in independent data analysis and interpretation of clinical study results; strong computer skills and interdisciplinary experience in statistical modeling and computer sciences, including ML; proficiency in Python and R with ML libraries (e.g., scikit-learn, XGBoost, TensorFlow); strong communication and publication track record.

Skills

• Independent data analysis and result interpretation
• Statistical modeling and ML across Python/R ecosystems
• Proficiency with ML libraries (scikit-learn, XGBoost, TensorFlow)
• Strong written and oral communication; ability to publish and present findings
• Data analysis and reporting proficiency
• Experience in drug safety not required

Education

• Ph.D. or PharmD in a relevant field (or equivalent advanced degree)

Additional Requirements

• This position is located in Indianapolis, Indiana (office-based); remote work is not considered.
• Fixed duration of two years with potential to extend to three years; opportunities to apply for full-time roles after completion.