Dr. Jin Zhou, Dr. Hua Zhou, and Dr. Gang Li of the Department of Biostatistics at UCLA are actively seeking a dedicated postdoctoral fellow with robust expertise in AI and statistics with applications to wearable devices, electronic health records, and statistical genetics at the scale of biobanks. The position will focus on methodological and applied work in either one of the two broad, complementary areas:

High-dimensional causal mediation and inference using AI methods
Developing and applying modern causal and statistical learning approaches for complex, high-dimensional data (e.g., multi-omics, imaging, rich clinical covariates) to understand mechanisms linking exposures, mediators, and health outcomes, with the application to chronic diseases such as diabetes and its complications.

AI and time series modeling for wearable device data and other longitudinal health data

Designing and evaluating AI-informed methods for long sequence modeling and forecasting of physiological signals (e.g., continuous glucose), integrating these data with electronic health records and other clinical information to support risk prediction, decision support, and adaptive interventions.

The postdoc will join an interdisciplinary team spanning biostatistics, data science, and clinical collaborators. The successful candidate will have substantial protected time for methodological research, as well as opportunities to work with rich real-world datasets and to contribute to collaborative papers and grant proposals.

Responsibilities
• Develop, implement, and evaluate new statistical and machine learning methods aligned with the two themes above.
• Lead and co-author manuscripts in statistical, machine learning, and clinical journals.
• Work closely with clinical and scientific collaborators to translate methods into applied analyses.
• Present work at conferences and internal seminars; contribute to a collaborative, inclusive research environment.