Senior LLM Systems Researcher — RAG & KV Cache

Huawei in Zürich is seeking a researcher with experience in LLM and RAG processes. You will design and implement RAG acceleration techniques, develop KV-cache reuse pipelines, and optimize performance using tools like PyTorch. Ideal candidates hold a PhD in Computer Science or a related field and possess strong communication and software engineering skills. This role offers competitive salary and professional growth opportunities in a dynamic work environment.
#J-18808-Ljbffr