Master Thesis in Evolutionary Design of Physically Interpretable Models Leveraging Generative AI

Company Description

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!

Job Description

The design of physical models for technical processes is typically a time-consuming and effortful task, particularly when physical interpretability is desired (as opposed to pure black-box modeling). Recently developed techniques that combine evolutionary algorithms with generative AI present a promising avenue for increasing the level of automation in the design of physically interpretable models.

• In your Master thesis, you will review the literature on the combination of evolutionary optimization and GenAI for optimization tasks (e.g., FunSearch, AlphaEvolve, etc.).
• You will deepen your understanding of the various aspects and approaches to designing physical models (static models, systems of differential equations).
• Additionally, you will assemble a set of modeling problems of increasing difficulty to benchmark different existing approaches. This includes designing metrics to compare models against each other in terms of accuracy and complexity.
• Furthermore, you will design, implement and evaluate methods that combine evolutionary algorithms and generative AI for the design of physically interpretable models, benchmarking them against black-box approaches and other interpretable methods (e.g., symbolic regression).

Qualifications

• Education: Master studies in the field of Mathematics, Physics, Electrical Engineering, Mechanical Engineering, Cybernetics, Computer Science or comparable
• Experience and Knowledge: proficient programming skills in Python; basic understanding of physical models, particularly dynamical systems (systems of differential equations in physics, electrical, or mechanical engineering); background in modeling dynamical systems and machine learning, preferably with experience in model evaluation (accuracy, complexity, generalization capabilities); background in optimization, preferably with experience in evolutionary/genetic algorithms; experience in using generative AI methods (e.g., LLMs) is a plus
• Personality and Working Practice: you are highly motivated for new challenges and have a structured working style
• Languages: very good in English and basic in German

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?
Dr. Benjamin Hartmann (Functional Department)
+49 7062 911 7020

#LI-DNI