Munich Thesis Autonomous Driving Simulation and Representation Learning BY 80809
Sign up free to see how well your resume matches this role.
What you'll do
- You support the exploration and implementation of methods for learning and improving high-level feature representations in E2E autonomous driving models.
- Furthermore, you help design and execute experiments using synthetic driving data (e.g., from CARLA) with flexible combinations of perception inputs and scene descriptions.
- In addition, you contribute to researching approaches such as representation learning, multi-modal learning, and sim-to-real transfer to improve model performance.
- Moreover, you support defining and evaluating suitable metrics and protocols to assess the quality of the learned representations.
- Furthermore, you help analyze experimental results, refine training pipelines, and contribute ideas to improve scalability.
- In addition, you support documenting your findings scientifically and presenting results to an interdisciplinary team.
What they're looking for
- Studies in computer science, robotics, electrical engineering, mathematics, physics or a related discipline.
- Strong programming skills in Python 3 and practical experience with deep learning frameworks such as PyTorch or TensorFlow.
- Solid understanding of machine learning and deep learning, ideally with a background in computer vision, representation learning, or domain adaptation.
- Practical experience or genuine interest in autonomous driving, driving simulators such as CARLA, or robotics.
- Familiarity with Linux, version control tools such as Git, and common libraries such as NumPy and pandas.
- Structured and proactive approach to application-oriented research with a clear link to real automotive use cases.
- Business-fluent English; German language skills are a plus.
Nice to have
- German language skills are a plus.
Summarised by NextRaise from the employer’s description, which follows in full below.
Full description from employer
Our team at the BMW Group focuses on next-generation end-to-end (E2E) autonomous driving systems and simulation technologies. We concentrate on learning robust, high-level internal representations that enable realistic and scalable simulation as well as data-efficient model development. As an intern, you support the investigation of how synthetic data from driving simulators can improve these representations and make them more applicable to real-world data.
What awaits you?
- You support the exploration and implementation of methods for learning and improving high-level feature representations in E2E autonomous driving models.
- Furthermore, you help design and execute experiments using synthetic driving data (e.g., from CARLA) with flexible combinations of perception inputs and scene descriptions.
- In addition, you contribute to researching approaches such as representation learning, multi-modal learning, and sim-to-real transfer to improve model performance.
- Moreover, you support defining and evaluating suitable metrics and protocols to assess the quality of the learned representations.
- Furthermore, you help analyze experimental results, refine training pipelines, and contribute ideas to improve scalability.
- In addition, you support documenting your findings scientifically and presenting results to an interdisciplinary team.
What should you bring along?
- Studies in computer science, robotics, electrical engineering, mathematics, physics or a related discipline.
- Strong programming skills in Python 3 and practical experience with deep learning frameworks such as PyTorch or TensorFlow.
- Solid understanding of machine learning and deep learning, ideally with a background in computer vision, representation learning, or domain adaptation.
- Practical experience or genuine interest in autonomous driving, driving simulators such as CARLA, or robotics.
- Familiarity with Linux, version control tools such as Git, and common libraries such as NumPy and pandas.
- Structured and proactive approach to application-oriented research with a clear link to real automotive use cases.
- Business-fluent English; German language skills are a plus.
Would you like to help advance autonomous driving through innovative representation learning and simulation techniques? Then Apply now!
What do we offer?
- Comprehensive mentoring & onboarding.
- Personal & professional development.
- Flexible working hours.
- Mobile work.
- Attractive & fair compensation.
- Apartments for students (subject to availability & only at the Munich location).
- And much more, see bmw.jobs/waswirbieten
Start date: Earliest start date 12.10.2026
Duration: 6 months
Working hours: Full-time
You can find helpful tips on your application and the application process here.
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. More about this here.
Company
Company facts come from this company's own listings. We only show what the postings themselves carry.