At Bosch, we shape the future by inventing high-quality technologies and services that spark enthusiasm and enrich people’s lives. Our promise to our associates is rock-solid: we grow together, we enjoy our work, and we inspire each other. Join in and feel the difference.

The Robert Bosch GmbH is looking forward to your application!

MEMS (Micro Electronic Mechanical Systems) make an important contribution to vehicle safety and are indispensable in consumer electronics. During the production and testing of these systems, large, heterogeneous data sets are generated that contain a variety of measured parameters. Knowledge Graphs (KGs) provide structured, semantically rich representations of domain knowledge, making them a powerful foundation for intelligent information retrieval. Retrieval-Augmented Generation (RAG) systems combine large language models with external knowledge sources to produce grounded, factually accurate responses. Recent work on GraphRAG has demonstrated the potential of combining these two paradigms. Current approaches have only begun to tap into the mature toolstack that the semantic web community has developed over decades.
The vision of this thesis is to expand upon state-of-the-art GraphRAG systems by leveraging semantic web technologies such as RDF, OWL, SPARQL, and ontology-driven reasoning to improve retrieval quality, answer accuracy, and faithfulness to the source data.

• During your thesis you will conduct a comprehensive literature review of GraphRAG systems, knowledge graph question answering, and relevant semantic web methodologies.
• You will investigate how symbolic approaches, ontological reasoning, and graph algorithms can complement or enhance existing retrieval and generation pipelines.
• Furthermore, you will design and implement a prototype system that integrates semantic web technologies into a GraphRAG architecture.
• Finally, you will validate your approach through extensive experiments on established public benchmarks as well as Bosch-internal datasets, comparing against current state-of-the-art baselines.

• Education: Master studies in the field of Computer Science, Machine Learning, Data Science, Cognitive Sciences or comparable with very good grades
• Experience and Knowledge: strong academic background in machine learning, graph data science, and/or semantic web technologies; comfortable in using Python with object-oriented coding practices; hands-on experience with the RDF-based semantic web stack (e.g., SPARQL, OWL, RDF libraries), graph data science tools, or RAG systems is a plus
• Personality and Working Practice: you excel at taking full ownership of open-ended research problems, demonstrating a motivated and proactive approach to learning and finding solutions
• Work Routine: we offer you the opportunity to work in a hybrid setup (60% on-site presence)
• Languages: very good in English, German is beneficial

Start: according to prior agreement
Duration: 6 months

Requirement for this thesis is the enrollment at university. Please attach your CV, transcript of records, examination regulations and if indicated a valid work and residence permit.

Diversity and inclusion are not just trends for us but are firmly anchored in our corporate culture. Therefore, we welcome all applications, regardless of gender, age, disability, religion, ethnic origin or sexual identity.

Need further information about the job?
Florian Diehl (Functional Department)
+49 157 557 65506

Work #LikeABosch starts here: Apply now!

#LI-DNI