LLM Inference Performance Engineer
AMD
Helsinki
Workplace: OnsiteFull timeFunction: OtherEducation: bachelorsSkills: ["Problem-solving","Communication","Collaboration","Initiative"]Role focused on performance analysis and optimization of production AI services within the AMD Inference Microservice ecosystem. You’ll measure, analyze, and optimize LLM/model performance across latency and throughput, build tooling for deployment performance, and collaborate across a fast-moving AI infrastructure team.

