Master Thesis on Graph Foundation Models for Enterprise Knowledge and Reasoning

About the role

We are looking for a motivated Master’s student to conduct a thesis on Graph Foundation Models (GFMs) within the Bosch ecosystem. The research will focus on automating the construction, completion and reasoning over enterprise knowledge graphs, supporting use cases such as root‑cause analysis in manufacturing.

Key responsibilities

• Perform a comprehensive literature review on state‑of‑the‑art GFMs and related graph analytics.
• Analyse existing benchmarks and datasets for knowledge‑graph construction, link prediction and graph‑based analytics.
• Develop and experiment with innovative GFM‑based models to extract entities and relationships from internal Bosch documents.
• Fine‑tune or prompt GFMs to infer missing links and predict relationships in Bosch knowledge graphs.
• Translate natural‑language queries into formal graph queries or use GFMs to reason over graph pathways.
• Evaluate model performance on academic benchmarks and real‑world Bosch datasets, assessing scalability, robustness and deployment potential.

Required profile

• Enrolled in a Master’s program in Computer Science or a related field.
• Strong academic background in machine learning and natural language processing.
• Proactive, independent research mindset with good problem‑solving skills.

Required skills

• Foundation models and transformer architectures.
• Deep learning frameworks such as PyTorch or TensorFlow.
• Knowledge of graph data structures and graph neural networks (a plus).
• Experience with machine learning and natural language processing techniques.