Master Thesis Causal Foundation Models for Enterprise Intelligence

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!

Large Language Models (LLMs) have revolutionized natural language processing, but they lack a true understanding of cause and effect. This limitation is a critical barrier to their application in high-stakes industrial domains, where understanding the "why" behind an event is crucial. Tabular foundation models, especially prior-fitted networks (PFNs), which are trained on synthetic data to eliminate the need for vast amounts of real-world data, have shown state-of-the-art performance in classification and regression. However, their application to causal tasks has hardly been explored.

• The goal of your thesis is to to combine the power of foundation models with functional causal models in order to solve causal inference tasks for enterprise applications at Bosch.
• You will conduct a comprehensive literature review on the current state of research into foundation models and their application to causal inference.
• Furthermore, you will develop new methods for foundation model-based causal tasks, with a focus on root cause analysis and test them on academic benchmarks and real-world use cases at Bosch.
• In addition, you will work and collaborate in a global research team.
• Ideally, your work will result in a scientific publication.

Qualifications

• Education: Master studies in the field of Computer Science or comparable, Bachelor's degree in Computer Science
• Experience and Knowledge:
  • strong academic background in machine learning and natural language processing
  • solid understanding of foundation models and transformer architectures
  • hands-on experience with deep learning frameworks (e.g., PyTorch, TensorFlow)
  • familiarity with graph data structures, graph neural networks and related concepts is advantageous
• Personality and Working Practice: you are a motivated, research-oriented individual who solves problems proactively and independently
• Work Routine: your partial on-site presence is required
• Enthusiasm: a keen interest in problem-solving
• Languages: business fluent in English

Additional Information

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?
Juergen Luettin (Functional Department)
+49 160 908 15759
Mirjam Steger (Functional Department)
+49 171 415250

Work #LikeABosch starts here: Apply now!

#LI-DNI