Research engineer with technical tesponsibility for AI-Based ultrasound diagnostics

Do you want to contribute to improving human health?

Would you like to take an AI-based decision-support system from research into clinical use? The department of clinical science and education, Södersjukhuset (KI SÖS), is seeking a research engineer to take technical responsibility for our platform for the ultrasound assessment of ovarian tumours, a class IIb medical device software under the EU MDR. You will be a key member of an interdisciplinary team of AI engineers, gynaecologists and ultrasound experts at KI SÖS, Södersjukhuset and KTH, and your work will have a direct impact on patients. The role involves independent responsibility for the platform’s architecture and its implementation in new healthcare settings.

The position is a fixed-term employment for one year. The scope of employment may vary between 50-100%, depending on the employee’s availability and the needs of the organisation. 

Your mission

As a research engineer, you will join professor Elisabeth Epstein's research group at KI SÖS. The work will also involve collaboration with professor Kevin Smith at KTH/SciLifeLab. Together, we develop and implement an AI-based decision-support system for the ultrasound assessment of ovarian tumours. The software is being developed as a medical device (Software as a Medical Device, Class IIb under the EU MDR). The aim is now to further develop the software for clinical use in new healthcare settings and for new applications, supported by a large multimodal dataset from Region Stockholm. As the technical lead, you will be responsible for the architecture, development, installation and operation of the platform, working closely with our AI engineers and clinical team. Your main tasks will be to:

• Own and further develop the service-oriented, event-driven architecture, which includes DICOM and email ingestion, data acquisition, image processing and AI inference, reporting and forwarding
• Install, configure and support the platform in different healthcare environments in collaboration with hospital IT departments, PACS administrators, and network and security officers
• Develop new functionality and new clinical applications together with our AI engineers and clinicians
• Manage inference pipelines for YOLO and classification models, including model versions, preprocessing, thresholds and reproducible configuration
• Build and maintain automated tests (unit, integration, end-to-end and regression tests) and DICOM simulation, as well as prepare verification documentation prior to releases.
• Securely manage configurations, secrets, certificates and trusted nodes across all installations
• Work in accordance with the project’s quality management system, IEC 62304 and ISO 14971, and contribute to lifecycle management, risk management, traceability, SOUP management and controlled releases
• Operate and troubleshoot the system, from logs and service errors to runtime behaviour

The role also involves travel to healthcare facilities within the region.

Your profile

You have a master of science in engineering or a MSc in computer science, engineering physics, biomedical engineering or equivalent, or professional experience. Furthermore, you have: 

• Several years of experience developing in Python, including type annotations, packaging, dependency management, logging and error handling
• Extensive experience using Docker and Docker Compose for development, testing and deployment
• Experience with service-oriented or event-driven systems, message queues, asynchronous processing and integration with external systems
• Experience with automated testing using pytest, Git/GitHub workflows and code reviews, as well as experience with Linux, networking and troubleshooting in production environments
• Excellent communication skills in English, both written and spoken

It is meritorious if you have: 

• Practical experience with DICOM (studies, series, instances, metadata, storage, routing and interoperability)
• Experience in medical device software development in accordance with the EU MDR, IEC 62304, ISO 14971 or IEC 81001-5-1
• Experience with system integration in hospital environments (PACS, HL7/FHIR)
• Experience running ML models in production, for example using PyTorch, ONNX or YOLO
• Experience with real-time image acquisition from video output and continuous inference
• Experience with GCP (databases, storage, container operations and secrets management), as well as JavaScript/React
• Experience with modern Python tools and static code analysis, such as uv, mypy and Pylint
• Good communication skills in Swedish, both written and spoken

As a person, you are independent and take initiative. You are qualityconscious and value reproducible and welldocumented work. You are creative and analytical when solving technical problems and flexible when conditions vary between healthcare environments. You collaborate well with clinicians, hospital IT staff and engineers. Previous experience in healthcare is a merit. In the assessment of applicants, particular emphasis will be placed on personal suitability. We would like the successful candidate to start as soon as possible.

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: SÖS

Gynaecology - Elisabeth Epstein's research group

Professor Kevin Smith, KTH

Choose to work at KI – Ten reasons why

Application

Welcome to apply no later than 30 October, 2026.

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. 

Permanent position is initiated by a six months trial period.

Want to make a difference? Join us and contribute to better health for all