Working Student (m/f/d) GenAI Evaluation & Testing

Aufgaben:

Maintain and expand eval sets: typical user questions, edge cases, «gold» expected outputs Build automated checks: format/structure validation, presence of sources, no-go patterns Implement regression tests: before/after comparisons, alerts in case of degradation Run benchmarks: compare quality/cost/latency; visualize results (scorecards/trends) and summarize briefly Support tooling/CI: small Python scripts, test runners, log analysis; basic CI checks within the team

Qualifikation:

Currently enrolled in a degree program (Computer Science, Data Science, Engineering, Mathematics, or similar) Solid Python basics, clean and reproducible working style; basic Git knowledge Interest in GenAI/LLMs and motivation to make quality systematically measurable Very good German and English language skills Structured way of working and strong willingness to learn

Über Uns:

KHS is a subsidiary of Salzgitter AG. As one of the world's leading manufacturers of filling and packaging systems for beverages and liquid food we are a world-class player. Our customers have trusted in our passionate pioneering spirit and first-class technologies for over 150 years. However, we can only remain world class if we continue to find new employees who make just as high demands of themselves and the quality of their work as our customers make Are you one of them? We are looking for a Working Student (m/f/d) in our AI Innovation Hub for our Dortmund location, starting as soon as possible, for 16-19 hours/week.