Detailansicht des Stellenangebots

Tätigkeitsbereich: Forschung & Entwicklung incl. Design
Fachabteilung: Scene Understanding
Gesellschaft: Mercedes-Benz AG
Standort: Sindelfingen
Startdatum: 23.06.2026
Veröffentlichungsdatum: 23.06.2026
Stellennummer: MER00041MO
Arbeitszeit: Full time

Aufgaben

The Mercedes-Benz Group AG is one of the most successful automotive companies in the world. Together with Mercedes-Benz AG, the vehicle manufacturer is one of the largest providers of premium and luxury cars and vans.

We are committed to shaping the future of automotive mobility by developing highly automated driving systems for both highway and urban areas. To achieve this, we are seeking highly motivated interns to support our research team on the topic of uncertainty estimation for end-to-end (E2E) autonomous driving within our Perception Team in Sindelfingen.

E2E autonomous driving models have emerged as a promising paradigm that directly maps sensor inputs to driving decisions. Compared to modular pipelines that separately process perception, prediction and planning, E2E models jointly optimize all stages within a single framework, resulting in simpler architectures and reduced information loss across modules. While architectural innovations have significantly improved model expressiveness and scalability, these systems are still prone to errors when encountering novel scenarios or unfamiliar appearances. To ensure safe decision-making, it is crucial to employ uncertainty estimation to identify potential errors such that they can be mitigated. However, the modeling and utilization of uncertainty along the E2E functional chain remain relatively underexplored. This research gap poses a critical challenge to the safety of autonomous systems in complex real-world environments.

Your role will involve investigating advanced uncertainty estimation methods and analyzing their applicability within the context of E2E AD. Additionally, you will aim to integrate these methods into the E2E AD system and analyze the effects of uncertainty on planning, especially in long-tail and rare scenarios. For this, you are expected to survey the state-of-the-art technologies in this domain and leverage advanced deep learning methodologies.

These challenges await you:

Conducting a comprehensive literature review on the current state-of-the-art methods in E2E driving and advanced uncertainty estimation techniques

Integrating and validating suitable uncertainty estimation methods within the E2E driving pipeline

Analyzing and utilizing these uncertainties along the E2E functional chain to evaluate their impact on planning tasks, particularly in novel and rare scenarios

Implementing and optimizing corresponding training and evaluation frameworks

Qualifikationen

Currently pursuing a master’s degree in computer science, robotics, physics, mathematics, electrical engineering, or adjacent fields

Strong programming proficiency in Python

Solid foundation and in-depth understanding of deep learning techniques, especially neural networks, and common software frameworks (e.g., PyTorch, MMDetection family)

Hands-on experience with Linux and development within Linux environments

Effective communication and collaboration skills

Fluency in spoken and written English

Preferred Qualifications:

Knowledge of perception, prediction, planning and uncertainty estimation

Publication at a deep learning or robotics conference (including collaborations)

Hands-on experience with containerization technologies (e.g., Docker)

Familiarity with LLM / VLM / VLAMs

Additional Information:

We look forward to receiving your online application, including a resume, cover letter, certificates, current certificate of enrollment stating your semester, proof of mandatory internship if applicable, and proof of the standard period of study. Please remember to mark your documents as "relevant for this application" in the online form and observe the maximum file size of 5 MB.

You can find further information on the hiring criteriahere .

Severely disabled applicants and applicants with equivalent status are welcome! The representative for severely disabled employees (sbv-sindelfingen@mercedes-benz.com) will gladly support you in the application process.

HR Services will be happy to help you with any questions you may have about the application process. You can reach us by email atmyhrservice@mercedes-benz.comor by phone at 0711/17-99000 (Mon-Fri 10am-12pm & 1pm-3pm).

Benefits

• Barriere­frei­heit
• Kantine, Café
• Kinder­betreuung
• Coaching
• Betriebs­arzt
• Mobilitäts­angebote
• Mit­arbeiter Events
• Mit­arbeiter­rabatte möglich
• Mit­arbeiter­beteili­gung möglich
• Mit­arbeiter­handy möglich
• Essens­zulagen
• Gesund­heits­maß­nahmen
• Hybrides Arbeiten möglich
• Betrieb­liche Alters­ver­sorgung
• Park­platz
• Gute An­bindung
• Flexible Arbeits­zeit möglich

Kontakt

Yutong Yang
Email: yutong.yang@mercedes-benz.com
Kolumbusstr. 19+21 Gebäude 711/0
71063 Sindelfingen