LLM Inference Optimization Engineer (GPU-Scale)

Rakuten Asia Pte. Ltd. in Singapore is seeking an LLM Inference Optimization Engineer to maximize performance and efficiency of large-scale inference on GPU clusters. You will optimize engines like vLLM, TensorRT-LLM, and Triton, and tune CUDA kernels to meet demanding SLOs. You will collaborate with infrastructure teams to deploy on Kubernetes, implement quantization, KV-cache management, and batching strategies, and stay current with AI inference research to push production performance. J-188…