Internship Agentic AI for Automated Code Generation in Safety-Critical Embedded Software

Bosch; Schwieberdingen; On-site; EUR 12,000 - 18,000; Full time

Job summary

Bosch Rexroth invites you to an internship focused on advancing our software processes for embedded systems. You will analyze development workflows, automate steps, and evaluate agentic coding tools for C/C++ on QNX and embedded Linux.

From day one you'll work on creating an agent pipeline that generates pull requests, including code, tests, static analysis, and CI builds, while aligning with ISO safety standards.

Qualifications

• Master studies in Computer Science, Software Engineering, Electrical Engineering, Information Technology, Mechatronics or comparable.
• Hands-on work with LLMs and AI coding assistants (e.g. Claude Code, GitHub Copilot).
• Experience with Git, CI/CD (e.g. GitHub Actions, Jenkins) and Linux.
• Very good Python skills, good working knowledge of C or C++.
• First practical experience in software development (internships, student jobs, projects).
• Ideally initial projects with LLMs beyond chat use.

Responsibilities

• Analyze current development process (requirements, coding, unit tests, reviews and integration).
• Evaluate state-of-the-art agentic coding tools for C/C++ on QNX and embedded Linux.
• Develop a process for creating an agent pipeline that generates a pull request including code, unit tests, static analysis and builds.
• Familiarise agents with a structured knowledge base, coding guidelines, and project rules.
• Address safety and security constraints, ensure traceability to requirements and ISO/IEC standards.
• Measure impact with KPIs and deliver a working prototype and rollout guidelines.

Skills

LLMs & AI coding assistants

Python

C/C++

Git

CI/CD

Linux

German (basic)

Education

Master's degree in Computer Science, Software Engineering, Electrical Engineering, Information Technology, Mechatronics or comparable

Tools

Git

Jenkins

GitHub Actions

QNX

Job description

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."

During your internship, you will analyze our current development process (requirements, coding, unit tests, reviews and integration), as well as identify the steps with the highest automation potential.

You will evaluate state-of-the-art agentic coding tools and frameworks (e.g. Claude Code, GitHub Copilot Agent Mode, MCP-based toolchains, multi-agent orchestration) for use with C/C++ on QNX, as well as embedded Linux.

In addition, you will develop a process for creating an agent pipeline that takes a requirement or ticket and generates a pull request. This will include code, unit tests, as well as static analysis (MISRA C/C++, clang-tidy) and builds, as well as tests in CI and self-correction loops.

Furthermore, you will familiarise the agents with our context using a structured knowledge base from the repository and architectural documentation, as well as coding guidelines, such as RAG, project rules and context engineering.

You will work on the addressing safety and security constraints, such as ensuring traceability to requirements, conducting human-in-the-loop reviews, as well as ensuring compatibility with ISO 13849/IEC 61508 and CRA-driven processes.

From the first day, you will be able to measure impact using clear KPIs, such as lead time per ticket, test coverage, defect rate, review findings and cost per feature. These will be compared against a manual baseline.

Last but not least, you will deliver a working prototype, guidelines for the teams in Germany, Poland and India, as well as a recommendation for rollout.

Education

Master studies in the field of Computer Science, Software Engineering, Electrical Engineering, Information Technology, Mechatronics or comparable

Experience and Knowledge

hands‑on work with LLMs and AI coding assistants (e.g. Claude Code, GitHub Copilot)

experience with Git, CI/CD (e.g. GitHub Actions, Jenkins) and Linux

very good Python skills, good working knowledge of C or C++

first practical experience in software development (e.g. through an internship, working student job, university projects or personal projects - GitHub link welcome)

ideally first projects with LLMs beyond chat use

Personality and Working Practice

you work independently, enjoy experimenting and present results clearly, as well as critically

Work Routine

your on‑site presence is required

Languages

business fluent in English; good in German is advantageous

— Published by Bosch.