184147 Published: 06.05.2026 Autonomous Driving Ulm New Autonomous Driving Ulm Ulm

BMW Group; Ulm; On-site; EUR 13,000 - 20,000; Part time

Job summary

BMW Car IT GmbH in Ulm offers a thesis opportunity on AI-driven map matching and path prediction for semantically enriched road networks. You will explore RDF-based connectivity, graph embeddings, and ML models to align GPS data with graph sequences and optimize predictions.

The role covers reinforcement learning framing, transformer-based sequence models, and graph-aware attention, with emphasis on robust, interpretable results and reproducible experiments.

Qualifications

• Pursuing a degree in CS, data science or a related field.
• Strong ML foundation and Python programming.
• Experience with PyTorch or TensorFlow.
• Knowledge of RDF/knowledge graphs is a plus.
• Strong German and English skills.

Responsibilities

• Support modeling road connectivity and constraints in RDF and implement rule sets to compute the most probable path using a rule-based reasoner.
• Help build features from observations and the road graph, learning graph embeddings and training models to predict the next link or path.
• Contribute to framing path prediction as a reinforcement learning problem, integrating graph embeddings and training agents such as DQN or actor-critic.
• Assist in developing sequence-to-sequence or transformer-based models to align GPS trajectories to graph-aligned edge sequences and compare to baselines.
• Experiment with graph-aware attention or constrained decoding to inject RDF structure and semantics into learning models.
• Design metrics and scenarios, measure accuracy, robustness, efficiency, and interpretability, and run ablations on embeddings and semantic attributes.

Skills

Machine learning

Python

PyTorch

TensorFlow

Graph representations

RDF/SPARQL

German language

English language

Version control

Education

Computer science

Data science

Electrical engineering

Tools

Git

SPARQL

RDF

Job description

Thesis on AI-Driven Map Matching and Path Prediction on Semantically Enriched Road Networks

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. 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.

Map matching and path prediction are core capabilities for autonomous driving. Our team at the BMW Group explores data-driven approaches that combine symbolic reasoning and machine learning, operating on real-world map data to improve robustness, accuracy, and interpretability in complex urban environments.

What awaits you?

• You will support modeling road connectivity and constraints in RDF and implementing rule sets to compute the most probable path using a rule-based reasoner.
• Furthermore, you help build features from observations and the road graph, learning graph embeddings and training models to predict the next link or path.
• In addition, you contribute to formulating path prediction as a reinforcement learning problem, integrating graph embeddings and training agents such as DQN or actor-critic.
• Moreover, you will assist in developing sequence-to-sequence or transformer-based models to align GPS trajectories to graph-aligned edge sequences and comparing them to baselines.
• Darüber hinaus wirkst du mit beim Experimentieren mit graph-aware attention oder constrained decoding to inject RDF structure and semantics into learning models.
• Additionally, you support designing metrics and scenarios, measuring accuracy, robustness, efficiency, and interpretability, and running ablations on embeddings and semantic attributes.

What should you bring along?

• Studies in computer science, data science, electrical engineering or a related field.
• Solid background in machine learning, including supervised learning and basic reinforcement learning.
• Experience with Python and machine learning or deep learning frameworks such as PyTorch or TensorFlow, plus data processing libraries.
• Familiarity with graph representations and knowledge graphs such as RDF and SPARQL; comfort with graph or knowledge graph embeddings is a plus.
• Understanding of graph neural networks or representation learning methods.
• Software engineering skills for reproducible experiments, including version control, clean code, and benchmarking.
• Good German and English skills.

What do we offer?

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

At the BMW Group, we place great importance on equal treatment and equal opportunities. Our recruiting decisions are based on the personality, experience, and skills of the applicants. Learn more here .

Thesis on AI-Driven Map Matching and Path Prediction on Semantically Enriched Road Networks

Legal Entity:

BMW Car IT GmbH

Location:

Ulm

Job Field:

Autonomous Driving

Job ID:

184147

Publication Date:

06.05.2026