Master thesis LLM Research (f/m/x)

SOME IT WORKS. SOME CHANGES WHAT'S POSSIBLE.

SHARE YOUR PASSION.

More than 90% of automotive innovations are based on electronics and software. That's why creative freedom and lateral thinking are so important in the pursuit of truly novel solutions. And that’s why our experts will treat you as part of the team from day one, encourage you to bring your own ideas to the table – and give you the opportunity to really show what you can do.

We, the BMW Group, offer you an interesting and varied Master thesis in the area of LLM and Generative AI research, specifically targeting ambiguity management in human-agent communication. With the growth of Language Model Learning (LLM), significant opportunities exist to advance the capability of voice assistants to effectively handle ambiguous user interactions. As an innovative, hands-on LLM developer, you will play a crucial role in enhancing our research platform for prototyping state-of-the-art, LLM-driven ambiguity detection and disambiguation mechanisms within an operational in-vehicle voice assistant.

What awaits you?

• Develop and implement methods to detect, categorize, and manage ambiguity in user requests within our LLM-based in-vehicle voice assistant.
• Introduce user-as-a-tool mechanisms to facilitate collaborative disambiguation, thereby enhancing interaction determinism, explainability, and user control.
• Create and prototype frameworks for prioritizing user requests, utilizing heuristics and leveraging contextual information (e.g., personal preferences, vehicle context, driving conditions) to resolve ambiguities effectively.
• Explore and implement algorithms designed for context-sensitive decision-making, clearly outlining the rationale for disambiguation choices to users.
• Collaborate closely with cross-functional teams to evaluate and refine approaches that improve explainability and controllability of interactions in ambiguous scenarios.
• Present your insights and progress regularly in team meetings and contribute actively to scientific research publications.

Please note that your thesis must be supervised by a university on your part.

What should you bring along?

• Enrollment in a Master's program in Computer Science or a related field.
• Strong proficiency in Python and familiarity with core frameworks relevant to LLM development, such as LangChain and Pydantic.
• Previous experience or interest in human-machine interaction, ambiguity detection, context-driven decision-making, and user-centric disambiguation in LLM applications is highly desirable.
• Demonstrated ability to collaborate effectively within an outstanding technical R&D team.
• Excellent written and verbal communication skills in English; German language proficiency is beneficial.

You are enthused by new technologies and an innovative environment? Apply now!

What do we offer?

• Comprehensive mentoring & onboarding.
• Personal & professional development.
• Flexible working hours.
• Digital offers & mobile working.
• Attractive remuneration.
• Apartment offers for students (subject to availability & only Munich).
• And many other benefits - see bmw.jobs/benefits

Earliest starting date: from 04/07/2025

Duration: 6 months

Working hours: Full-time

Do you have any questions? Then simply send your enquiry using our contact form. Your enquiry will then be answered by telephone or e-mail.

At the BMW Group, we see diversity and inclusion in all its dimensions as a strength for our teams. Equal opportunities are a particular concern for us, and the equal treatment of applicants and employees is a fundamental principle of our corporate policy. That is why our recruiting decisions are also based on personality, experience and skills.

Find out more about diversity at the BMW Group at bmwgroup.jobs/diversity