The Department of Medical Epidemiology and Biostatistics conducts research in epidemiology and biostatistics across a broad range of areas within biomedical science. The department is among the largest of its type in Europe and has especially strong research profiles in psychiatric, cancer, reproductive, pediatric, pharmaco, genetic, and geriatric epidemiology, eating disorders, and biostatistics. Our department consists of researchers, doctoral students, biostatisticians, data collectors and database administrators as well as administrative personnel, in total some 270 staff. The department is situated at campus Solna. Further information can be found at ki.se/en/meb.
The research group is affiliated with the national Data Driven Life Sciences (DDLS) program and SciLifeLab (https://www.scilifelab.se/researchers/kimmo-kartasalo/). We conduct international cutting-edge research in computational pathology and artificial intelligence (AI). Specifically, the group has for several years worked with AI-based models to assist pathologists in their assessment of prostate biopsies.
The core competences of the group include large-scale image processing and analysis, development of deep learning based AI algorithms, and efficient utilization of supercomputing systems. Our backgrounds range from computer science and mathematics to biotechnology and medicine, and we embrace a highly collegial and flexible working culture.
The aim of the project is to develop and evaluate artificial intelligence (AI) methods for computational pathology. Specifically, the project focuses on training and validating a vision transformer (ViT)-based foundation model (FM) using large collections of digitized prostate core needle biopsies. The developed prostate-specific foundation model will be benchmarked against state-of-the-art foundation models trained on diverse organs and diseases.
The successful candidate will contribute to research activities involving model development and implementation, computational optimization, and large-scale data processing. Working closely with researchers in computer science, statistics, and biomedicine, you will support the development and evaluation of AI methods for clinically relevant applications in prostate cancer. The project will investigate downstream tasks relevant to prostate cancer patient management, including cancer detection, grading, and prognostic prediction. The data collection and preprocessing required for the project have already been completed.
Your responsibilities will include:
-
Contributing to the development and training of a prostate-specific foundation model for digital pathology.
-
Establishing and maintaining pipelines for evaluating the model on clinically relevant downstream tasks.
-
Benchmarking the developed model against state-of-the-art foundation models and reporting results.
-
Supporting large-scale computational experiments using GPU-based computing infrastructure.
The position is a full-time employment of 3 months (July 2026 – September 2026).
The applicant is expected to possess the following skills and experience:
-
Experience of processing whole slide image data from Leica, Hamamatsu, Philips and Grundium scanners using libraries such as OpenSlide or OpenPhi.
-
Experience of training pathology foundation models, particularly for prostate cancer applications.
-
Knowledge of parallel computing, GPU programming, CUDA, or computational optimization.
-
Experience handling and analyzing large-scale datasets.
-
Experience working in Linux environments.
-
Familiarity with Python.
-
Familiarity with version control tools e.g. Git.
-
Ability to work well independently and together with others.
-
Ability to communicate with colleagues in English.
The following skills and experience are considered meriting:
-
Hands-on experience with DINO/iBOT-style self-supervised vision transformers.
-
Experience with statistical modelling, probability theory, or biostatistics.
-
Knowledge of and interest in pathology, oncology or other relevant medical fields.
-
International and interdisciplinary research experience.
Other knowledge in biomedicine, digital pathology or computer science is an advantage. Great emphasis is placed on personal qualities in this recruitment: a successful applicant should be communicative, responsible, accurate, structured and result-oriented in their work.
A creative and inspiring environment with wide-ranging expertise and interests. Karolinska Institutet is one of the world's leading medical universities. Our vision is to pursue the development of knowledge about life and to promote a better health for all. At Karolinska Institutet, we conduct successful medical research and hold the largest range of medical education in Sweden. Karolinska Institutet is also a state university, which entitles you to several good benefits through our collective agreement. And you get to practice freely in our modern wellness facilities, where trained staff are on site.
Location: Solna
Choose to work at KI – Ten reasons why
KI applies individual and differentiated salary setting in accordance with our collective agreements RALS and RALS-T.
The application is to be submitted through the Varbi recruitment system.In this recruitment, you will apply with your CV without a personal letter. Instead, you will answer some questions about why you are applying for the job in the application form.
Anställningsform: tidsbegränsad anställning | Anställningens omfattning: heltid | Antal lediga befattningar: 1 | Sysselsättningsgrad: 100 | Ort: Stockholm | Län: Stockholms län | Land: Sweden | Referensnummer: STÖD 2-2397/2026 | Kontakt: Kimmo Kartasalo , Kimmo Kartasalo , | Facklig företrädare: Ann Almqvist, SACO , Ann Almqvist, SACO , Elizabeth Valenzuela, SEKO , Elizabeth Valenzuela, SEKO , Bodil Moberg , OFR/ST , Bodil Moberg , OFR/ST , | Publicerat: 2026-06-01 | Sista ansökningsdag: 2026-06-23
