Student for Master's Thesis - Agentic AI in CarIT Security

Life is always about becoming... In life it is about going on a journey to become the best version of our future self. As we discover new things, we face challenges, master them and grow beyond us.

Apply to Mercedes-Benz and find the area where you can develop your talents individually. You will be supported by visionary colleagues who share your pioneering spirit. Joining us means becoming part of a global team whose goal is to build the most desirable cars in the world. Together for excellence.

Number: MER00046QC Mercedes-Benz Group AG is one of the most successful automotive companies in the world. With Mercedes-Benz AG, the vehicle manufacturer is one of the largest providers of premium and luxury cars and vans. The cybersecurity of our vehicles decides whether software-defined functions come safely into the market and remain safe there. Car IT Security is responsible for vehicle cybersecurity across the entire product life cycle – from threat analysis and security requirements to the backup of ECU software, key material and update processes to the detection of regulatory and homologation. A growing share of this work consists of knowledge-intensive, highly distributed tasks over request, ticket and documentation systems – precisely there this work is starting. These challenges come to you: Analysis of the state of the art of agentic AI (LLM-based agents, tool usage, orchestration of several agents, retrieval on specialist knowledge) and evaluation of transferability to safety-critical engineering processes Development of an evaluation framework that sets up tasks for suitability for agentic support, taking into account criticality, traceability and necessary human release points Concept of a reference architecture for an agentic assistant including connection to existing tool chains (requirement and ticket systems, code repositoryes, knowledge databases), rights and data concept as well as guardrails and human-in-the-loop gates Prototypical implementation of at least one use case in the existing tool landscape and testing on real, shared specialist contents of the area Quantitative and qualitative evaluation of the prototype (including quality of results, reproducibility, processing time, error and hallucination behavior) compared to today's manual procedure Classification in regulatory and normative frameworks (including ISO/SAE 21434, UN ECE R155, EU AI Act, internal AI and information security requirements) and deriving requirements for a responsible operation deriving an action recommendation with scaling path, operating model and open risks as well as presentation of results in the field of expertise The final topics will be discussed with the university, you and us. The activity can begin from September 2026.

Computer Science, IT Security, Electrical Engineering, Automotive Engineering, Mechatronics, Business Informatics, Data Science or Comparable Basic knowledge of IT and Cybersecurity, ideally first touch points with Automotive Security (ISO/SAE 21434, UN ECE R155) or embedded systems Interest in or first practical experience with generic AI, Large Language Models, Prompting and Agent or Automation Frameworks programming knowledge, preferably python, as well as safe handling of common development and collaboration tools Secure knowledge of German and English in word and writing Safe handling of MS Office Commitment and team skills Analytical way of thinking and structured self-responsibility and the willingness to work into a regulatory environment

Additional information: We are looking forward to your online application with CV, lettering, certificates, current enrollment certificate with an indication of the semester and proof of the regular study period. Please do not forget to mark your documents as ''relevant for this application' in the online form and to observe the maximum file size of 5 MB. Further information on the setting criteria can be found here. Disabled and equalized applicants are welcome! The severely disabled representative (sbv-sindelfingen@mercedes-benz.com) is happy to support you in the application process. People Solutions will be happy to help you with questions about the application process. You can reach us by email via myhrservice@mercedes-benz.com or by phone at 0711/17-99000 (Mo-Fr 10-12am & 13-15am).

Food supplements Employee handy possible Employee discounts possible Employee participation possible Staff Events Coaching Flexible working time possible Hybrid work possible Health measures Employment Mobility offers Parking space Business doctor Good connection Accessibility Child care Kantine, Café