Protecting Health Information. Ensuring Data Integrity.
Protecting Health Information. Ensuring Data Integrity.

Postdoctoral Fellowship: Applications of Machine Learning Methods to Synthetic Data Generation

The Electronic Health Information Laboratory (EHIL) is seeking one postdoctoral fellow to join our research program for at least one year. The research topic is synthetic data generation (SDG) using statistical machine learning and deep learning methods. This includes the development of new SDG methods, evaluating the utility and disclosure risk of the synthetic datasets, plus developing new utility and privacy metrics.

SDG is emerging as an important set of techniques for enabling ready access to health data. This allows health research and innovation to occur, whether in academia or in industry. The potential impact of high utility and privacy preserving synthetic data can be nontrivial, on data access and also on our ability to accelerate clinical research by simulating virtual patients.

EHIL conducts multi-disciplinary research to enable data sharing and data simulation. It is located at the Children’s Hospital of Eastern Ontario Research Institute. Our research results get applied in practice relatively quickly, so we get rapid feedback from practice to continue improving our work.

Remote candidates will be considered, although we would want to be able to meet with him/her in person at some point during the fellowship. The position is available to start immediately.


  • A recent PhD in statistics, computer science, applied mathematics, engineering, epidemiology, or a similar discipline.
  • Good knowledge of R and/or Python, and ideally PyTorch.
  • Previous work in statistical disclosure control, developing and evaluating machine learning models.


Please send your resume to Elizabeth Jonker at:

We will get back to you if there is a good fit to arrange for interviews with our team.