Working Student - LLM Quantization & Inference Performance
Labels
- Language
- English only
“Clear communication and the ability to present experimental findings and technical tradeoffs to the team.”— from the posting
- Type
- Working student
“We’re looking for a motivated working student to help turn these questions into experiments”— from the posting
About this role
Working student role at an AI inference hardware startup in Munich, focused on evaluating how LLM quantization affects model quality and runtime. The student will implement post-training quantization methods, build reproducible evaluation tooling, and measure latency, throughput and memory. Applicants should be enrolled in a master's program in a related field and have strong Python and PyTorch skills.
From the original posting
About Tensordyne (formerly Recogni) AI is transforming our world. It can perform cognitive functions that previously only humans could do, such as perceiving interactions across different modalities and environments - with the ability to quickly learn and then solve complex problems. Tensordyne is…
Read the full posting ↗What this means for you
- Working students (Werkstudenten) are regular part-time employees, so the minimum wage applies (€13.90 per hour).
- Working more than 20 hours a week during the semester can end your working-student status for social insurance. Non-EU students: these working days count toward your limit of 140 full / 280 half days per year.
- The posting doesn't mention pay. It's normal to ask about the Praktikumsvergütung before you accept an offer.
- EU/EEA and Swiss students have no work-day limit and can work like German students.
General information, not legal advice. Rules can change and your situation may differ — check with your university, the employer or your Ausländerbehörde.