Research Fellow (m/f/x) in AI for Autonomous Scientific Discovery and Scientific Machine Learning

In order to fill a fixed-term position in full-time (39.83 hours/week = 100%) at the earliest possible date, we are looking for a

Research Fellow (m/f/x) in AI for Autonomous Scientific Discovery and Scientific Machine Learning

The chair "Simply Complex Lab" focuses on understanding, controlling, and predicting emergent phenomena far from thermodynamic equilibrium. Its research is at the intersection of soft condensed matter, complexity, nonequilibrium, and nonlinear physics and interfaces with materials science, nanotechnology, and mechanobiology. The very nature of the lab’s research program is interdisciplinary; it is led by experiments but also strongly theory-guided.

As a research fellow (m/f/x), you will focus on developing scientific machine learning and AI-microscopy integration methods that can analyse experimental data streams and actively guide experiments through feedback.

Scope: full-time

Duration: fixed-term, 12 months (project duration)

Start: at the earliest possible date

Apply by: 2026-11-03

Your tasks:

Reinforcement Learning for Autonomous Experiments (Primary Focus)

• Develop actor-critic and related reinforcement learning algorithms for experimental control.
• Design reward functions for pattern optimisation, exploration, and rare-event discovery.
• Investigate autonomous strategies for navigating high-dimensional experimental parameter spaces.
• Implement learning frameworks capable of operating on live experimental data streams.

Machine Learning and Pattern Recognition (Secondary Focus)

• Develop methods for crystal structure identification.
• Designed supervised and unsupervised learning approaches for pattern classification.
• Build models that identify precursors to structural transitions and emergent behaviour.
• Integrate multimodal imaging data into robust machine learning workflows.

Scientific Discovery and Analysis

• Analyse large-scale microscopy datasets.
• Develop quantitative measures of order, disorder, and structural evolution.
• Investigate mechanisms underlying non-equilibrium self-organisation.
• Publish findings in leading journals and conferences.

Your profile:

• An academic degree in Machine Learning, Artificial Intelligence, Computer Science, Physics, Applied Mathematics, Engineering, or a closely related field.
• Strong experience in machine learning research.
• Experience developing and evaluating reinforcement learning algorithms.
• Strong Python programming skills.
• Experience with PyTorch and/or TensorFlow.
• Experience working with large datasets and scientific computing.
• Excellent scientific communication (written and oral) and collaboration skills.

[[external link]