The Department of Computer Science (DIKU) at the University of Copenhagen is recruiting a PhD fellow for the “Differentiable Realism from AI and Modeling” (DREAM) project, funded by the Novo Nordisk Foundation. The project aims to build machine learning methods that rely on simulated data where labelled biological data is scarce or expensive to obtain.
The role
- Develop simulation-supervised machine learning methods for microscopy image data
- Build biophysical simulations that automatically tune themselves to match experimental data more closely
- Apply differentiable programming in JAX or PyTorch, including differentiable rendering or physics-based models
- Research methods to close the gap between simulated and real data (domain adaptation)
- Apply the methods to chromatin organisation or DNA structure analysis from microscopy images
Requirements
- Strong background in computer science, machine learning, scientific computing, physics or applied mathematics
- Experience with machine learning, deep learning or generative modelling
- Experience with computer vision, differentiable programming, numerical simulation or computational biology data is an advantage
- A degree equivalent to a Danish master’s degree (180 ECTS bachelor’s plus 120 ECTS master’s)
About the employer
The project sits in the IMAGE research group at the Department of Computer Science, University of Copenhagen, one of the largest research universities in the Nordic region.
Salary and deadline
This is a full-time position for up to 3 years. Employment is conditional on enrolment as a PhD student, and pay follows the agreement between the Danish Ministry of Taxation and the Danish Confederation of Professional Associations (AC); the ad does not state a specific salary figure. The expected start date is 1 January 2027.
The application deadline is 15/09/2026 at 23:59. The ad does not state whether remote or hybrid work is possible.
Source: University of Copenhagen, “PhD Fellowship in Simulation-Supervised Machine Learning for Biology”, read 11 September 2026. Summary by AVIDE; see the original page for the full and current text.