PhD Positions in Agentic AI for Medical Image Analysis

Kennziffer: 2026-0230

• Heidelberg
• Full-time
• Medical Image Computing

Das Deutsche Krebsforschungszentrum (DKFZ) ist eines der größten Krebsforschungszentren Europas. „Forschen für ein Leben ohne Krebs“ ist unsere Mission und hierfür arbeiten unsere Weltklassewissenschaftler:innen gemeinsam mit allen Mitarbeitenden.

Wir erforschen, wie Krebs entsteht, erfassen Krebsrisikofaktoren und suchen nach neuen Strategien, die verhindern, dass Menschen an Krebs erkranken. Wir entwickeln neue Methoden, mit denen Tumore präziser diagnostiziert und Krebspatient:innen erfolgreicher behandelt werden können. Jeder Beitrag zählt – ob in der Forschung, in der Administration oder der Infrastruktur. Das macht unsere tägliche Arbeit so bedeutungsvoll und spannend.

The Division of Medical Image Computing (MIC) at the German Cancer Research Center (DKFZ) in Heidelberg, starting in January 2027, is offering

The Division of Medical Image Computing (MIC) is recruiting PhD candidates to develop AI agents that interpret medical images, use analysis tools, evaluate intermediate results, and adapt their approach based on evidence and feedback.

Candidates will join a collaborative research environment with clinical partners, extensive computing infrastructure, and connections to initiatives such as Helmholtz Imaging.

Ihre Aufgaben: 

We investigate how AI agents can combine medical images with clinical information, plan and execute analytical steps, learn from feedback, assess intermediate results, and respond appropriately to uncertainty or failure. Approaches may include reinforcement learning, multimodal learning, vision-language models, planning, tool-augmented language models, probabilistic modelling, and classical medical image analysis.

Candidates may work primarily in one of several application areas:

1. multimodal agents for prostate cancer diagnosis and treatment support;
2. auditable analysis of longitudinal imaging for tumour-response assessment;
3. federated multimodal agents connecting oral imaging with systemic health information; or
4. or reinforcement learning for agents that navigate and integrate complex data across medical and other scientific domains.

The individual PhD topic will be developed jointly based on the candidate’s interests, expertise, and the methodological questions arising across these applications.

You will:

• develop agents that combine medical images with clinical text and other information;
• investigate reinforcement learning for planning, tool use, feedback integration, and iterative improvement;
• apply agentic methods to segmentation, annotation, quantitative analysis, or scientific data exploration;
• establish rigorous evaluation methods covering accuracy, robustness, generalisation, uncertainty calibration, failure detection, and appropriate abstention; and
• collaborate with methodological and clinical researchers, publish your results, and contribute reusable software or benchmarks.
  

Ihr Profil:

You should have:

• A master’s degree in computer science, data science, mathematics, physics, engineering, or a related discipline
• A strong foundation in machine learning and strong Python programming skills
• Practical experience with a deep-learning framework such as PyTorch
• Experience in at least one relevant area, such as reinforcement learning, computer vision, language models, multimodal learning, or medical-image analysis
• An analytical and collaborative working style and good communication skills in English

Previous experience with medical data is helpful but not required. We also welcome candidates with strong machine-learning fundamentals who want to develop expertise in agentic AI.

What you can excpect: 

• Scientific freedom to develop your own methodological research question
• Close supervision and exchange within a cohort of PhD researchers
• Access to extensive GPU infrastructure, medical-imaging resources, and established research software
• Collaboration with international machine-learning and clinical partners
• Support for conference participation, open-source contributions, and professional development
• Fully funded PhD submission

Please submit:

• your CV
• academic transcripts
• a brief research statement of no more than one page describing a question in agentic AI that interests you
• your preferred application area, or a ranking of the available areas
• your master’s thesis or another representative piece of scientific work
• links to relevant publications, software, or code repositories, if available
• Instead of a generic motivation letter, please use your research statement to explain which scientific question you would like to investigate, why it matters, and how you might approach it
  

Unser Angebot:

Sie sind interessiert?

 ​Befristung: Die Stellen sind zunächst auf 3 Jahre befristet.

Bewerbungsschluss: December 2, 2026

Bewerbungen per E-Mail können leider nicht angenommen werden. ​
Bitte beachten Sie auch, dass wir per Post eingereichte Bewerbungen nicht zurückschicken können.

Wir sind davon überzeugt: Ein innovatives Forschungs- und Arbeitsumfeld lebt von der Vielfalt seiner Beschäftigten. Daher freuen wir uns über Bewerbungen von talentierten Menschen, unabhängig von Geschlecht, kulturellem Hintergrund, Nationalität, ethnischer Zugehörigkeit, sexueller Identität, körperlichen Fähigkeiten, Religion und Alter. Menschen mit Schwerbehinderung werden bei gleicher Eignung bevorzugt.

 

Hinweis: Wir unterliegen den Vorschriften des Infektionsschutzgesetzes (IfSG). Deshalb müssen alle unsere Beschäftigten einen Immunitätsnachweis gegen Masern vorlegen.

 

 

Teilen Sie diesen Job!