Working student: GenAI Evaluation & Testing (m/f/d)

Working student: GenAI Evaluation & Testing (m/f/d)

KHS is a subsidiary of Salzgitter AG. As one of the world's leading manufacturers of filling and packaging systems for beverages and liquid foods, we operate at a world-class level. For over 150 years, our customers have relied on our passionate pioneering spirit and our first-class technologies. But we can only remain world-class if we continually find employees who demand the same high standards of themselves and the quality of their work as our customers demand of KHS. Are you one of them?

We are looking for a working student (m/f/d) for 16-19 hours/week at our Dortmund location in the area of ​​AI Innovation Hub, starting as soon as possible.

Your tasks

• Maintaining and expanding evaluation sets: typical user questions, edge cases, and "gold" answers
• Develop automatic checks: format/structure checks, source checks, no-go pattern detection
• Implement regression tests: Before/after comparisons and alerts for quality losses.
• Conduct benchmarks: measure quality, costs, and latency; visualize and briefly summarize the results.
• Supports tooling and CI: small Python scripts, test runners, log analysis, and simple CI checks.

Your profile

• Enrolled in a degree program (e.g., computer science, data science, engineering, mathematics, or similar)
• Basic knowledge of Python and Git basics (Branch/PR)
• Very good German and English skills
• Structured work style and high willingness to learn
• Interest in GenAI/LLMs

our range

• Independent work with room for own ideas
• Hands-on work on productive GenAI systems
• Learn how teams integrate quality gates, regression, and benchmarks into releases.
• The advantages of a collectively agreed remuneration
• Location: Dortmund | North Rhine-Westphalia
• Type of employment: Working student position