Thesis AI Agent for Automated Machine Diagnostics and Root-Cause Analysis

Bosch Group; Elchingen; On-site; EUR 10,000 - 12,000; Full time

Benefits offered by this job

On-site work

Job summary

Bosch Rexroth is seeking a thesis kandidaat to develop an AI agent that analyzes machine behavior directly from CAN measurements and derives solutions for calibrations, software, and hardware issues. You will build the agent harness, custom skills, and tools to enable it on a digital test bench.

The role requires on-site collaboration, with experience in Python, LangChain, and signal analysis. Start is February 2027 for a 3–6 month period, enrolled at university.

Qualifications

• Enrollment at university is required.
• Strong Python development skills and knowledge of AI workflows.
• Familiarity with LangChain and agentic workflows is a plus.
• Basic knowledge of control systems and signal analysis is expected.

Responsibilities

• Develop an AI agent that analyzes machine behavior from CAN measurements and derives diagnostics across calibrations, software bugs, or hardware issues.
• Create the agent harness, custom skills, and necessary tools or MCP servers to enable it.

Skills

Python development

LangChain

Agentic workflows

Signal analysis

Control systems

Education

Electrical Engineering

Mechatronics

Computer Science

Tools

LangChain

CAN bus data analysis

Job description

Thesis AI Agent for Automated Machine Diagnostics and Root-Cause Analysis

At Bosch Rexroth, everything revolves around movement and the success of our customers. With our networked drive and control technologies as well as digital solutions, their machines and systems work efficiently, safely and powerfully. We offer components, system solutions and services for mobile and industrial applications as well as for factory automation. In all areas, we value the know-how and commitment of our employees and enable dynamic careers in an international environment.

Around 33,800 people in over 80 countries - and one corporate purpose: "We move industries to make our planet a better place."

• Full-time

• During your thesis, you will build a reliable agent that analyzes a user's machine behavior directly from CAN measurements and derives solutions across calibrations, software bugs, or application/hardware issues.


• You will create the agent harness, custom skills, and necessary tools or MCP servers to enable it (e.g. with LangChain).


• Furthermore, you will set up automated signal and event detection routines to capture anomalies such as limit violations, oscillations, derating, and error states.


• You will prepare appropriate context for the agent, integrating relevant documentation, parameters, and domain knowledge.


• Additionally, you will benchmark the agent against established reference cases to assess its accuracy and reproducibility.


• Moreover, you will automate the simulation loop by replaying measurements within a virtual test bench (e.g., TPT) to cross-compare simulated dynamics with measured behavior.


• Finally, you will document the developed tool and present your findings and methodology to the team.

• Education: studies in the field of Electrical Engineering, Mechatronics, Computer Science or comparable


• Experience and Knowledge: inPython development, LangChain, Agentic Workflows; basic knowledge of control systems and signal analysis


• Personality and Working Practice: you excel at analyzing challenges critically, driving innovative solutions, and learning continuously while communicating openly with others


• Work Routine: your on-site presence is required


• Enthusiasm: for AI workflows, Agents and Applications


• Languages: fluent in English and very good in German

Start: February 2027
Duration: 3 - 6 months

Requirement for this thesis is the enrollment at university.

As a global company, we are legally required to comply with applicable EU and U.S. (re-)export control and sanctions regulations. This means that for certain, particularly sensitive positions, we may only hire individuals who have undergone an additional legal screening. This position is one such sensitive role. We will therefore ask you for additional information required for this screening as the application process continues. You can find information about the processing of your data in our Privacy Notice for the application process.

Diversity and inclusion are not just trends for us but are firmly anchored in our corporate culture. Therefore, we welcome all applications, regardless of gender, age, disability, religion, ethnic origin or sexual identity.