GPU-Accelerated LLM Inference Engineer

Rakuten Asia Pte. Ltd. in Singapore is seeking an LLM Inference Optimization Engineer to maximize the performance, efficiency, and scalability of large-scale inference workloads on GPU clusters. You will optimize engines and GPU kernels to ensure peak model serving efficiency. The role requires deep expertise in CUDA/Triton, inference internals, and experience with at least one serving engine. Collaboration with global teams across Rakuten will be essential. J-18808-Ljbffr