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

Siemens AG · Erlangen · 35 hours a week

ThesisGerman needed: none

Still open on 1 Nov

You apply on the company's own website.

Key facts

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

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

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 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

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

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