Student Assistant for LLM-Based Research in the »Quantum Machine Learning« Team (all genders)

The »Quantum Machine Learning« team at Fraunhofer Institute for Industrial Engineering IAO in Stuttgart conducts research on quantum computing-based data processing and develops machine learning methods in support of quantum technologies. The team is part of flaQship, the Fraunhofer Lab for applied quantum computing Stuttgart-Heilbronn, which unites the expertise of Fraunhofer Institute for Industrial Engineering IAO and the Fraunhofer Institute for Manufacturing Engineering and Automation IPA. Within flaQship, the research area Quantum Service Engineering and High-Performance Computing focuses on making quantum computing usable as service-oriented applications, on integrating quantum resources into existing IT workflows, and on operating the laboratory and High-Performance computing infrastructure on which our research, trainings and demonstrators rely.

To strengthen our research activities, we are looking for a Student Assistant interested in exploring how large language models and agentic AI systems can support research in quantum algorithms and related fields. You will contribute to the development and evaluation of AI-assisted research workflows that combine scientific literature, mathematical reasoning, software tools, and automated verification to accelerate and improve research in quantum computing.

Be part of change

• You explore how large language models and AI agents can support research in quantum algorithms, quantum software, compilation, simulation, and related fields

• You develop prototypes of agentic research workflows for tasks such as literature exploration, algorithm comparison, circuit generation, resource estimation, and automated experimentation

• You connect AI agents with scientific tools, including quantum software frameworks, numerical simulators, symbolic mathematics systems, literature databases, and code repositories

• You design benchmarks and test cases to evaluate mathematical correctness, physical consistency, reproducibility, and practical usefulness

• You investigate and compare approaches such as prompting, retrieval-augmented generation, tool use, planning, reflection, and multi-agent systems

• You analyze failure modes, including hallucinated references, incorrect derivations, invalid quantum circuits, unreliable code, and misleading claims of quantum advantage

• You implement and evaluate proof-of-concept systems in Python and assess their applicability in scientific research workflows

• You document methods, experiments, and results in a reproducible manner and contribute to internal reports, presentations, software tools, and scientific publications

• You regularly discuss your progress, findings, and research ideas with the project team and contribute to shaping future research directions