Senior AI Performance Engineer - LLM Inference

AMD is seeking a senior engineer to push AI inference performance on GPUs using vLLM. You will own end-to-end profiling, optimization and measurable uplifts across client deployments.

The role requires deep knowledge of vLLM internals, GPU kernels, and distributed systems; applicants should have 5+ years in GPU computing and strong Python/C++ skills. Helsinki-based role with collaboration across teams.