🔬 About the Field: MRI Predictive Modeling with AI
Magnetic Resonance Imaging (MRI) stands at the forefront of medical diagnostics, providing unmatched detail in soft tissue imaging. However, traditional MRI faces a significant challenge: lengthy scan times of 30-40 minutes per patient due to complex signal acquisition processes. The emerging field of predictive modeling using artificial intelligence aims to revolutionize this by developing intelligent systems that can optimize MRI configurations in real-time, dramatically reducing scan times while maintaining diagnostic quality. This cutting-edge research combines deep learning, medical physics, and computer engineering to create foundation models that can adapt to different patient anatomies and clinical scenarios, ultimately making MRI faster, more efficient, and more accessible to patients worldwide.
📌 Position Overview
✅ Salary: €3,059 – €3,881 gross per month (increasing from year 1 to year 4)
✅ Duration: 4-year PhD position (1.5-year initial contract + 2.5-year extension after assessment)
✅ Institution: TU Delft, Faculty of Electrical Engineering, Mathematics & Computer Science
✅ Location: Delft, Netherlands
✅ Hours: 36-40 hours per week (Full-time)
✅ Additional Benefits: 8% holiday allowance + 8.3% end-of-year bonus
✅ Application Deadline: January 17, 2026
🔬 Research Focus
This PhD position is part of the SAMURAI project, a national collaboration with Philips Medical Systems. You will work on developing AI-based solutions for predictive intelligence in MRI scanning, specifically:
- Designing efficient foundation models for generalization across patient anatomies and pathologies
- Developing system architectures to enable learning from heterogeneous MRI data
- Creating techniques to convert partial MRI measurements into optimal sensor configurations
- Integrating domain knowledge about MRI physics into machine learning models
- Addressing integration challenges with existing medical procedures
🎯 Requirements
✅ MSc degree in Electrical Engineering, Computer Engineering, Computer Science, or related field
✅ Good understanding of computer architecture
✅ Understanding of AI and its practical implementations
✅ Ability to work in a team and take initiatives
✅ English proficiency (for doctoral education courses and scientific writing)
📄 Application Documents Required
✅ CV
✅ 1-page motivational letter tailored to this position
✅ Papers or written work demonstrating your writing and scientific skills
📧 How to Apply
Address your application to Prof. Dr. Ir. Georgi Gaydadjiev
🔗 Step-by-Step Application Guide
1️⃣ Visit the official TU Delft careers page for this position
2️⃣ Click the “Apply now” button on the job posting
3️⃣ Create an account or log in to the TU Delft application portal
4️⃣ Fill in your personal information and contact details
5️⃣ Upload your CV in PDF format
6️⃣ Upload your 1-page motivational letter (tailored to the position)
7️⃣ Upload sample papers or written work showcasing your scientific writing skills
8️⃣ Review all information carefully before submission
9️⃣ Submit your application before January 17, 2026
🔗 Apply here: https://careers.tudelft.nl/job/Delft-PhD-Position-on-Predictive-Modeling-of-Magnetic-Resonance-Imaging-2628-CD/1348790257/
📧 Contact for Questions:
Prof. Dr. Ir. Georgi Gaydadjiev: g.n.gaydadjiev@tudelft.nl
Dr. Ir. Motta Taouil: m.taouil@tudelft.nl
🌟 Additional Perks
- Enrollment in TU Delft Graduate School with excellent supervision and mentorship
- Doctoral Education Programme for transferable skills development
- Customizable compensation package
- Discounts on health insurance
- Monthly work costs contribution
- Flexible work schedules
- Relocation support through “Coming to Delft Service”
- Dual Career Programme for accompanying partners
🖖 About TU Delft
Delft University of Technology is a top international university combining science, engineering, and design. Known for creating world-famous Dutch waterworks and pioneering in biotech, TU Delft delivers world-class results in education, research, and innovation to address challenges in energy, climate, mobility, health, and digital society.
Serving