Master thesis AI-Driven Geospatial Data Fusion Leveraging Machine Learning (f/m/x)

Bayerische Motoren Werke Aktiengesellschaft; München; Vor Ort; EUR 60.000 - 80.000; Vollzeit

Zusammenfassung

A leading automotive company in Munich is offering a master's thesis opportunity focused on AI-driven geospatial data fusion. The successful candidate will contribute to enhancing autonomous driving technologies through innovative data integration strategies, leveraging advanced techniques like Graph Neural Networks. This is a full-time position starting from November 2025, and students must ensure university supervision for the thesis.

Leistungen

Mobile work options

Student apartments available

Qualifikationen

• Proficiency in Python with machine learning libraries required.
• Familiarity with Graph Neural Networks and Graph Attention Networks preferred.
• Proactive mindset with problem-solving skills.

Aufgaben

• Advance technologies in autonomous driving through data integration.
• Explore innovative solutions for fusing geospatial data.
• Develop knowledge graphs for semantic data integration.

Kenntnisse

Programming in Python

Machine Learning

Problem-Solving

Graph Theory

Ausbildung

Studies in machine learning or related field

Jobbeschreibung

Press Tab to Move to Skip to Content Link

Master thesis AI-Driven Geospatial Data Fusion Leveraging Machine Learning (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. Our experts will treat you as part of the team from day one, encouraging you to bring your ideas and giving you the opportunity to showcase your skills.

With the rise of geospatial technologies and digital mapping, data sources such as road networks, traffic conditions, lane configurations, and GPS-based sensor data are being generated at an increasing rate. Integrating this data for road network modeling presents challenges like heterogeneity, fragmentation, noisiness, and the complexity of topological relationships.

What awaits you?

• You will contribute to advancing autonomous driving technologies through geospatial data integration.
• In your master's thesis, you will explore innovative solutions for fusing diverse geospatial data sources, addressing challenges such as data heterogeneity and complexity in road network modeling.
• You will leverage a hybrid approach combining Graph Neural Networks and Graph Attention Networks to discover patterns in road networks and model map data semantically.
• Additionally, you will develop a knowledge graph to capture the semantics of geospatial data, facilitating the integration of graph embeddings with machine learning models for improved performance and efficiency.

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

What should you bring along?

• Studies in machine learning, data analysis, or a related field.
• Proficiency in programming languages such as Python, with experience in machine learning libraries and frameworks, especially for graph-based models.
• Familiarity with graph theory and neural network architectures, particularly Graph Neural Networks and Graph Attention Networks.
• A proactive mindset and problem-solving skills to tackle complex data integration challenges.
• A passion for innovation and a desire to contribute to the future of mobility through advanced data-driven solutions.

Are you enthusiastic about new technologies and an innovative environment? Apply now!

What do we offer?

• Mobile work options.
• Student apartments (subject to availability, only at the Munich location).

Start date: from 08/11/2025
Duration: 6 months
Working hours: Full-time

If you have questions, submit your inquiry via our contact form. We will respond by phone or email.

At the BMW Group, we value equal treatment and opportunities. Our hiring decisions are based on personality, experience, and skills. Learn more here.