Intern MB.CO - AI ready Interface Documentation & Agent Prototype (Arazzo / MCP)

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: MER000446K Mercedes‐Benz develops and builds vehicles worldwide. In order to be successful in the long term, strategic decisions must be taken at an early stage, well-founded and coordinated over many areas. Strategic planning is a central lever for this. It forms the basis for long-term product and portfolio decisions, cost-effectiveness and investment assessments, supplier awards, capacity and production decisions as well as many other company-wide questions. For this purpose, different scenarios are developed, tested and compared with one another – across different disciplines. For this to work efficiently, several IT systems need to work closely together and exchange data cleanly through interfaces. Only if these interfaces are clearly described, reliably linked and consistently used can strategic planning work efficiently. At the same time, we must create the foundations for these relationships to be understood and used independently by AI agents in the future – as a basis for intelligent, strategic planning of the future. These challenges include: AI agents can only help if You really understand the underlying system and data relationships. The aim of the internship or master thesis is to prepare our interface landscape AI‐ready and to test these assumptions directly. To do this, you standardize the connections between interfaces and implement an AI agent as a proof of concept that automatically retrieves the correct data about the correct interfaces and links information from multiple systems. In concrete terms, we proceed as follows: Win an overview of the interface landscape Understand which interfaces exist, which data You provide and how You are used today.

Descriptive interfaces Building a comprehensive description of how multiple interfaces interact along typical end-to-end processes (e.g. with Arazzo, a standard for describing processes across multiple APIs).

Technically make use of AI Connect selected interfaces so that an AI agent can call them (e.g. with MCP, a standard for the uniform use of APIs by AI agents).

React AI Agent as Proof of Concept Implementation of an agent that utilizes the relationships described and independently develops the correct data from the correct interfaces.

Optional deepening: Multi-Agent approach (ACP) Investigate whether the tasks can be better implemented by a central AI agent or by several specialised agents working together via a defined communication mechanism (for example, using ACP – Agent Communication Protocol).

The activity can begin from August 2026.

enrolled:r Student:in a relevant course of studies, e.g. computer science, business informatics, data science, software engineering or a comparable technical course

Programming skills in TypeScript/JavaScript or Python

Basic understanding of APIs (REST, HTTP, JSON)

Ability to document complex technical relationships in a structured manner

Good knowledge of German and English

Self-working and pleasure to work on new technologies independently

First practical experience in the programmatic implementation and testing of AI agents

Experience with OpenAPI / Swagger

Experience in the deepened programmatic development of AI agents, including API integration, workflow logic or agent orchestration (e.g. Arazzo, MCP, ACP)

What you're doing Insight into strategic planning and the IT landscape of a large industrial company

Work on a topic with direct benefit today (better end-to-end documentation) and strategic benefit tomorrow (base for more complex AI agents)

An independent project with clear deliverables in future-relevant technologies and standards

Additional information: We are looking forward to your online application with CV, lettering, certificates, current enrollment certificate with a specification of the semester, if necessary. Compulsory internship certificate 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 note 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. HR Services 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