PhD - Neurosymbolic Reasoning for Domain-Adaptive Generative AI
Bosch Gruppe sucht: PhD - Neurosymbolic Reasoning for Domain-Adaptive Generative AI in Renningen. Der Job ist als Vollzeit ausgeschrieben. veröffentlicht am 05.11.2026.
- Arbeitgeber
- Bosch Gruppe
- Ort
- Renningen
- Beschäftigungsart
- Vollzeit
- Veröffentlicht
- 05.11.2026
Aufgaben und Anforderungen: PhD - Neurosymbolic Reasoning for Domain-Adaptive Generative AI bei Bosch Gruppe
Do you want beneficial technologies being shaped by your ideas? Whether in the areas of mobility solutions, consumer goods, industrial technology or energy and building technology - with us, you will have the chance to improve quality of life all across the globe. Welcome to Bosch.
The Robert Bosch GmbH is looking forward to your application!
Employment type: Limited
Working hours: Full-Time
Joblocation: Renningen
Aufgaben
Large Language Models (LLMs) have demonstrated remarkable capabilities across a wide range of tasks. However, their performance often degrades in highly specialized domains that require precise structural reasoning, consistency, and domain-specific knowledge. In electronic hardware design, existing LLMs struggle with the structural and semantic complexity of circuit descriptions. Hardware designs are represented as interconnected graphs, including netlists, schematics, and hierarchical design projects. These representations carry essential information that is lost when converted into purely sequential text.
- As a part of our team, you will research novel methods for adapting generative AI systems to specialized domains by integrating structured symbolic knowledge, without relying on extensive model retraining.
- Your investigation will focus on mechanisms that enable Large Language Models (LLMs) and other foundation models to leverage external knowledge representations such as knowledge graphs, ontologies, and formal design representations while preserving the reasoning capabilities of symbolic systems.
- You will develop innovative approaches that enable generative AI models to interact directly with these structured representations, allowing for more precise reasoning, design assistance, verification, and code generation.
- Through your work, you will make a key contribution to the development of next-generation AI systems that combine the flexibility of neural models with the reliability, interpretability, and structured reasoning capabilities of symbolic representations.
Profil
- Education: excellent Master's degree in Computer Science, Mathematics, Engineering, or a related field
- Experience and Knowledge: solid knowledge of computer science, artificial intelligence, machine learning, data science, or electrical engineering; experience with deep learning, graph algorithms, and knowledge representation; knowledge of hardware design is an advantage
- Personality and Working Practice: you approach interdisciplinary research questions with curiosity and creativity, engage openly with others, communicate your ideas clearly, and actively seek out new challenges
- Languages: fluent in English, German is a plus
Wir bieten
- Work-life balance: Flexible working in terms of time, place and working model.
- Health & Sport: Wide range of health and sports activities.
- Childcare: Intermediary service for childcare services.
- Employee discounts: Discounts for employees.
- Room for creativity: Space for creative work.
- In-house social counseling and care services: Social counselling and intermediary service for care services.
The recruitment contact or superior will be happy to provide information about the individual benefit plan.
WEFS1_DE