Thesis (Master): Evaluation of Standardized Physical Device Interaction by AI Agents

Siemens AG; Bayern; Hybrid; EUR 12,000 - 19,000; Full time

Benefits offered by this job

Supervision by experts

Labs and equipment access

Career opportunities

Job summary

Siemens AG in Erlangen is seeking a Master's Thesis student to explore how AI agents can autonomously discover, control, and safeguard physical devices using standardized device descriptions. You will evaluate LLM-driven approaches and compare standards (MCP, MHS, OPC UA, WoT, AsyncAPI) to assess token use, expressiveness, and safety.

The position emphasizes hands-on research with modern hardware interfaces. Join the Foundational Technologies division for a fixed-term, full-time thesis project.

Qualifications

• Currently enrolled in a Master’s program in Computer Science, Electrical Engineering, Robotics, or a related field.
• Strong proficiency in Python; knowledge of C/C++ and Rust is beneficial.
• Experience with LLM integration and agentic AI software development.
• Basic understanding of hardware-software interfaces and measurement technology, with an interest in industrial communication protocols such as OPC UA and Web of Things.

Responsibilities

• Evaluate the performance of large language models (LLMs) in semantic discovery tasks.
• Analyze and compare description standards—MCP, MHS, OPC UA, Web of Things, AsyncAPI.
• Research methods to deterministically extract hardware safety limits from device metadata.
• Investigate approaches for autonomous authentication and access control in dynamic environments.

Skills

Python

C/C++

Rust

LLM integration

Agentic AI

Hardware interfaces

OPC UA

Web of Things

Education

Master's student in CS/EE/Robotics

Tools

OPC UA

Web of Things

AsyncAPI

MCP

MHS

Job description

Thesis (Master): Evaluation of Standardized Physical Device Interaction by AI Agents

Job ID

524349

Posted since

08-Oct-2026

Organization

Foundational Technologies

Field of work

Internal Services

Company

Student (Not Yet Graduated)

Job type

Full-time

Hybrid (Remote/Office)

Employment type

Fixed Term

Location(s)

Mode of Employment:Fixed Term / Full-Time; (35 hours / week)

Future autonomous systems, such as mobile robots, must be capable of dynamically adapting to their environment by utilizing available hardware as tools. Instead of relying on pre-programmed drivers, these systems should autonomously discover and interface with devices on-the-fly. This thesis explores how Large Language Models (LLMs) can bridge the gap between high-level intent and physical hardware interaction through standardized device descriptions.

What´s the goal

Ready to bring the future of AI-driven hardware interaction to life? Join us in Erlangen as a Master's Thesis student and help pioneer how intelligent agents autonomously discover, control, and safeguard physical devices in real-world environments!

What we offer you

• Exciting research and development projects that put your theoretical knowledge into practice
• Individual supervision and support from experienced experts in your field
• Access to the latest technologies, laboratories, and resources
• Diverse opportunities to contribute your ideas and actively shape the projects
• Excellent career opportunities through contact with potential employers

You’ll make an impact by

• You currently study successfully in a field such as Computer Science, Electrical Engineering, or a related discipline, applying your academic knowledge to real-world device interaction challenges
• Building on this foundation, you evaluate the performance of large language models (LLMs) in semantic discovery tasks, probing and mapping unknown physical devices via various industrial communication protocols
• Subsequently, you analyze and compare description standards—such as MCP, MHS, OPC UA, W3C WoT, and AsyncAPI—to assess their impact on token consumption, expressiveness, interface quality, safety, and reliability
• In addition, you research and implement methods to deterministically extract hardware safety limits from device metadata, ensuring the absence of physical damage during autonomous operation
• Finally, you investigate approaches for autonomous authentication and access control, contributing to the secure configuration of devices in dynamic, ad-hoc environments

This is how you’ll win us over

• Education: You are currently enrolled in a Master's program in Computer Science, Electrical Engineering, Robotics, or a related field
• Experience and Skills
  • Strong proficiency in Python; knowledge of C/C++ and Rust is beneficial
  • Experience with LLM integration and agentic AI software development
  • Basic understanding of hardware-software interfaces and measurement technology, with an interest in industrial communication protocols such as OPC UA and Web of Things
• Ways of Working: You work independently and thrive on exploring complex, innovative system architectures
• Languages: Very good English skills are required

You are much more than your qualifications, and we believe in the potential of every single candidate. We look forward to getting to know you!

At Siemens, we believe that feeling valued and included is the foundation for doing great work. That’s why we aim to create an inclusive workplace where everyone feels a sense of belonging, and where individual perspectives and experiences are celebrated. Our commitment to fairness and respect extends to every applicant.

As an equal opportunity employer , we welcome applications from individuals of all backgrounds and particularly encourage applications from persons with disabilities.

About Us

The world never stands still. And new challenges arise every day. With a passion for questioning things, for supplying ideas, and intelligently driving things forward we are helping society move towards a smarter tomorrow. Be it with technologies that reduce carbon emissions in cities or hyperintelligent robots. This is how we are able, to tackle the most important projects and push them forward together. Help us shape the future.

FAQ – if you need further information on the application process.