Two Research Assistants in AI for Breast Cancer Decision Support Full-time

Two Research Assistants in AI for Breast Cancer Decision Support

Do you want to contribute to top quality medical research?

We are looking for two research assistants to join a new five-year EU Horizon Europe project on AI for multidisciplinary breast cancer care. The positions are full-time and limited to one year, with the possibility of extension. There are good opportunities, in the case of mutual interest, to apply for a fully funded doctoral position at Karolinska Institutet. Such a position requires a separate application process and that KI's admission requirements for doctoral studies are met.

The Research Group

The research group is led by Fredrik Strand, MSc MD PhD, who has a mixed background of medicine, engineering and economics, and is a breast radiologist at the Karolinska University Hospital. Lead AI scientist and day-to-day supervisor is Apostolia Tsirikoglou, MSc PhD. In total, there are around ten full-time members of the group: research specialists, postdocs, PhD students, research engineers and radiologists. Our research is internationally recognized for the development and evaluation of AI for radiological breast cancer diagnostics with recent publications in Lancet Digital Health, JAMA Oncology, Radiology, MICCAI, among others. Our group has expertise in radiology, machine learning and biostatistics. We have a strong collaboration with research groups at KTH, others at KI, and internationally within three EU projects and with a group at Computational Precision Health at University of California Berkeley.

A New Horizon Europe Project – GenAI4Care

The GenAI4Care project (2026–2031) will be carried out in a consortium of 24 partners across 14 countries with the aim to build a generative multi-agent AI virtual assistant (VA) for breast cancer that integrates insights from specialized AI agents into context-aware, explainable, and patient-centered decision support across the care continuum. The system is designed to augment multidisciplinary tumor board (MTB) reasoning around patients. Karolinska Institutet (KI) leads the breast cancer use case and Real-World Evaluation (WP8) and contributes substantially to agent development and system instantiation. Karolinska University Hospital (KS) participates as KI's affiliated entity with clinical experts in surgery, oncology, pathology, and radiology. The other two clinical partners in the breast cancer use case are: the Medical University of Gdańsk, Poland, and the Royal Marsden National Health Service Trust, United Kingdom.

This is not a quiet lab project – you will collaborate with an international consortium, contribute to EU deliverables, travel to consortium meetings, and work at the intersection of AI research and clinical practice.

Your Mission

The two research assistants will work across the technical and clinical dimensions of the project. The exact division of tasks will depend on the candidates' profiles and interests, but collectively the work covers three main areas:

AI agent development. Building core AI agents for the breast cancer virtual assistant, covering tumor detection in mammography and MRI, tumor characterization, and prognostic modelling. The work spans model adaptation and training, integration of explainability methods (SHAP, Grad-CAM, LIME), containerization (Docker), and benchmarking against clinical baselines and commercial solutions. Later phases include scenario simulation, counterfactual reasoning, conflict resolution, and multi-agent orchestration.

Data engineering and system integration. KI is a primary data provider and deployment site. The work includes extracting and harmonizing clinical data from hospital systems (EHR, PACS, digital pathology, national quality registries), building data pipelines using health data standards (OMOP, HL7/FHIR, DICOM), contributing to the project's Data Management Plan, and managing the local deployment and integration testing of the multi-agent platform. You will work at the interface between KI's clinical IT systems and the consortium's technical infrastructure.

Clinical evaluation and validation. KI leads the clinical evaluation of the system. Both positions will contribute to structuring multimodal clinical data, designing evaluation protocols, and working closely with the four hospital clinicians to annotate cases, develop decision-state representations, conduct simulated MTB evaluations, and assess the clinical usefulness, trustworthiness, and robustness of the AI system in real-world settings. This includes retrospective studies across multiple European sites and analysis of decision-making processes.

General Duties. In addition to these project-specific tasks, the research assistants are expected to contribute to study design, statistical analysis, interpretation of results, scientific writing, and dissemination of findings at international conferences.

Your Profile

Necessary:

• A Master's degree (or equivalent experience) in a relevant field: computer science, biomedical engineering, health informatics, data science, applied mathematics, or similar
• Proficiency in Python
• Experience with quantitative data analysis and statistical reasoning
• Strong analytical ability and interest in interdisciplinary research at the interface of AI and medicine
• Excellent written and spoken English
• Ability to collaborate across disciplines – you will work with clinicians, engineers, and researchers from across Europe
• A strong personal interest to improve cancer care

Desirable/advantageous:

• Experience with deep learning for image analysis, particularly medical imaging (mammography, breast MRI, digital pathology)
• Familiarity with health data standards (FHIR, OMOP, DICOM) or clinical data systems
• Experience with model containerization (Docker) or deployment infrastructure (Kubernetes)
• Familiarity with explainability methods, fairness evaluation, or trustworthy AI
• Experience with data harmonization, ETL pipelines, or database systems
• Familiarity with risk prediction, survival analysis, or decision modelling
• Experience with training or fine-tuning machine learning or deep learning models

Terms and Conditions

These are full-time research assistant positions. There are good opportunities, in the case of mutual interest, to apply for a fully funded doctoral position at Karolinska Institutet. Such a position requires a separate application process and that KI's admission requirements for doctoral studies are met.

What Do We Offer?

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

Application

Karolinska Institutet invites applications for up to two research assistant positions within an internationally leading research environment focused on AI-supported breast cancer care. We welcome applicants with different profiles and strengths – please describe in your cover letter which aspects of the work interest you most.

Submit your application and supporting documents through the Varbi recruitment system. Use the button in the top right corner and follow the instructions.

Your application should contain the following five documents:

• A cover letter describing your background, which aspects of the work interest you most, and why this role appeals to you (max 2 pages)
• A curriculum vitae
• Transcripts from your highest university degree (showing grades)
• Degree projects, theses, or publications, if any
• Contact details for 1-2 references (you can choose to share this later after the first interview)

Selection

A selection will be made among applicants on the basis of their ability to contribute to the project's research goals. The qualifications of the applicants will be evaluated on an overall basis.

Karolinska Institutet uses the following bases of assessment:

• Documented subject knowledge of relevance to the area of research
• Analytical skill
• Other documented knowledge or experience that may be relevant to the position

All applicants will be informed when the recruitment is completed.

The position is initially for 1 year, with possibility of extension.

Apply at the latest 26th May.