I develop and maintain the Java-based backend services for the EESSI project for The Danish Agency for Labour Market and Recruitment, facilitating secure and efficient electronic exchange of social security information across EU member states. I utilize technologies such as Spring, RESTful APIs, and the ELK-stack to enhance system performance and reliability.

I develop data science solutions, primarily within the field of Natural Language Processing (NLP), for various government departments, achieving cost savings for the government through data-driven optimization and efficiency improvements, as well as enhance the employee job satisfaction by providing data-driven solutions that streamline their work processes.

Working with NLP-related machine learning methods, primarily NER models. My work is mostly done in Python, however, I have also worked with Docker.

Improving 2D human pose estimation for bouldering by incorporating the temporal information of a video by using deep learning models. Developed in Python through PyTorch and trained on a multi-GPU SLURM-cluster.

TA'ing the course "Modelling and Analysis of Data (NDAB16012U)" at the University of Copenhagen.