Job Description
Job Title:  Research Fellow (CQM/SE)
Posting Start Date:  21/07/2025
Job Description: 

Job Description

The Centre for Quantitative Medicine (CQM) in Duke-NUS Medical School invites applications from outstanding candidates to join a talented team of data analysts, methodologists and biostatisticians supporting cutting-edge research in a world-class academic medical centre. The School embodies a strategic partnership between Duke University and National University of Singapore. It works closely with the Singapore Health Services (SingHealth) cluster, a network of national specialty disease centres, hospitals and polyclinics, to advance medicine and improve lives through cutting-edge research and education. CQM is an academic centre for quantitative scientists and strives to bring the quantitative science and biomedical research communities together.

We invite applications for a Research Fellow/Senior Research Fellow position for development of risk prediction models in Neurology using EEG data via Deep Learning (DL) techniques. In this prospective and longitudinal study, the outcome of interest is cognition over time. This position will be under the supervision of Assistant Professor Seyed Ehsan Saffari. The duration of this position is 1 year with the possibility of a 1-year extension

The main responsibilities of the successful candidate will include but not limited to the following: -  
•     Develop the DL-based rick models.
•     Collaborate on DL projects within the lab. 
•     Write scientific reports and contribute on research grant proposals. 
•     Join journal clubs. 
•    Conduct a wide range of neural network analysis

Job Requirements

The project requires a researcher with a   
•    PhD in Computer Science, Biostatistics, Statistics or other related fields  
•    Prior experience in analysing EEG data.  
•    Possess strong programming skills (mostly Python) and familiar with statistical methods. 
•    Have good communication and writing skills.,  
•    Interest in developing risk prediction models via deep learning/machine learning.
•    Have strong background in DL, EEG data and programming for the implementation of proposed methods.