Modern X-ray free-electron lasers (XFELs) have transformed how scientists study molecular and material structures. Their unique beam properties are crucial for experiments, but optimizing these features, especially advanced ones such as the wavefront shape, is a complex and time-consuming endeavor. Moreover, the lack of near-real-time feedback from experiments to the XFEL machine prevents immediate beam adjustments, resulting in inefficient use of valuable experimental time and limiting XFEL's full scientific potential.

In this project, AI4Ops@XFEL, we propose optimizing X-ray free-electron laser (XFEL) operation through AI-driven real-time feedback, addressing critical challenges in optimizing beam parameters and maximizing data quality. By integrating machine learning into experimental diagnostics, this project aims to unlock AI-based control over XFEL beam properties, building the foundation for significantly enhancing experiment quality.

Requirements:

• Master's degree (or equivalent) in computer science (or a closely related degree program) with a grade of "good” or better according to the German or ECTS grading scale
• expertise in deep learning, modern DNN architecture such as attention and transformers, and/or reinforcement learning
• expertise in Efficient ML, Edge AI and/or TinyML
• background (or strong interests) in physics, especially quantum mechanics, particle physics, and accelerator physics

Position:

• Hamburg University of Technology
• 100% EGR. 13 (TVöD) position for three years

The TUHH values diversity, therefore all applications are welcome, regardless of gender, gender identity, ethnic origin, nationality, age, religion and belief, disability, sexual orientation and identity or social background.

The TUHH stands for equal opportunities as well as appreciative and respectful cooperation.