Master Thesis Causal Foundation Models for Enterprise Intelligence

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.

• 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