Data Scientist with Interest in synthetic data modelling

Dsts; Aalborg; On-site; DKK 45,000 - 70,000; Full time

Job summary

Dsts is seeking a data scientist to join the Center for Clinical Data Science at Aalborg University. This role focuses on developing a national sandbox infrastructure for health data science, emphasizing synthetic data generation and safe data sharing.

The ideal candidate will collaborate with a team of data scientists and manage specific data types. The position aims to produce realistic synthetic datasets for various applications in health data science research.

Qualifications

• Experience in health data science.
• Ability to work with synthetic health data generation.
• Familiarity with privacy measures and data utility.

Responsibilities

• Develop the sandbox infrastructure for health data science.
• Support users and manage selected types of data.
• Implement measures on dataset utility, fidelity, and privacy.

Job description

Center for Clinical Data Science, Department of Clinical Medicine, Aalborg University is hiring a data scientist for a national “sandbox” infrastructure in health data science. The position is for two years with a possibility for extension. Starting date will be July 1, 2023, or as soon as possible.

The main task of the data scientists is to develop the sandbox infrastructure. You will be responsible for developing a part of the infrastructure and for supporting users. You will work closely together with four other data scientists at the other participating universities, and you will be mainly responsible for some selected types of data and corresponding tools. This role will especially focus on synthetic health data generation and implementation of measures on dataset utility, fidelity, and privacy, a field gaining a lot of traction as a way to support safe data sharing and project development in health data science research. The aim is to provide realistic but safe-to-share synthetic datasets that simulate patient histories, electronic health records, lab records, and/or medical images, etc, for use in teaching, training, tool development (algorithm/model/platform), and project design.