LLM Inference Optimization Engineer (GPU)

Rakuten Asia Pte Ltd; Singapore; On-site; SGD 120,000 - 180,000; Full time

Job summary

Rakuten Asia Pte Ltd in Singapore invites an experienced LLM Inference Optimization Engineer to join our AI & Data Division. You will optimize large-scale inference workloads on GPU clusters, implement quantization and caching strategies, and collaborate with global teams to maximize throughput and minimize latency.

You will work with vLLM, TensorRT-LLM, Triton, and custom kernels on NVIDIA hardware, while profiling performance and driving SLO-aligned improvements in a fast-paced, international

Qualifications

• 3+ years of hands-on experience optimizing deep learning inference on NVIDIA GPUs.
• Strong knowledge of LLM inference internals: attention, KV cache, batching, quantization.
• Experience with at least one mainstream inference engine (vLLM, SGLang, TensorRT-LLM, Triton).
• Proficiency in CUDA and/or Triton kernel programming, with a solid understanding of modern GPU architecture.
• Strong software engineering fundamentals in Python and C++.
• Bachelor's or higher degree in Computer Science, Engineering, or related field.

Responsibilities

• Profile, optimize, and extend modern LLM inference engines (e.g., vLLM, SGLang, TensorRT-LLM) to improve throughput, latency, and GPU utilization.
• Design and implement inference-time optimizations such as quantization, KV-cache management, continuous batching, speculative decoding, and parallelism strategies.
• Develop and tune GPU kernels (CUDA, Triton) for critical operators — attention, GEMM, MoE.
• Build benchmarking and load-testing frameworks to measure end-to-end serving performance under realistic workloads and SLOs.
• Partner with infrastructure teams to deploy and scale inference on Kubernetes-based GPU clusters, including autoscaling, fault tolerance, and observability.

Skills

LLM inference

CUDA / Triton

Python

C++

GPU profiling

Education

Bachelor's degree in CS/Engineering

Tools

vLLM

SGLang

TensorRT-LLM

Triton Inference Server

Nsight Systems

Job description

Rakuten Asia Pte Ltd in Singapore invites an experienced LLM Inference Optimization Engineer to join our AI & Data Division. You will optimize large-scale inference workloads on GPU clusters, implement quantization and caching strategies, and collaborate with global teams to maximize throughput and minimize latency.

You will work with vLLM, TensorRT-LLM, Triton, and custom kernels on NVIDIA hardware, while profiling performance and driving SLO-aligned improvements in a fast-paced, international