Working Student - LLM Quantization & Inference Performance

Overview

Tensordyne is hiring a Working Student for LLM Quantization & Inference Performance based in Munich, Bavaria, Germany. The role focuses on exploring optimization methods, building reusable evaluation tooling, measuring runtime performance, and conducting quantization research to help optimize models for Tensordyne hardware.

Who can apply

Applicants must be currently enrolled in a master's degree program in Computer Science, Mathematics, Electrical Engineering, Machine Learning, or a related field. Candidates need strong Python and PyTorch skills, the ability to effectively use AI coding tools, an experimental mindset, and clear communication skills. Experience with quantization, LLM evaluation, performance profiling, or inference optimization serves as a strong plus.

What you get

The position offers the opportunity to join a deep-tech team building the next generation of AI inference systems. Working students receive close mentorship from experienced engineers, own a focused project, and gain practical experience with leading open-source large language models while deepening their understanding of inference optimization and quantization.