AMD GPU Inference Performance Engineer

INFERACT SINGAPORE PTE. LTD.; Singapore; On-site; SGD 167,000 - 335,000; Full time

Benefits offered by this job

Equity

Medical insurance

Dental

Job summary

Inferact seeks an AMD GPU performance engineer to advance vLLM as a premier inference engine on AMD accelerators. You will build and optimize AMD GPU backends, kernels, runtime paths, and benchmarking infrastructure to deliver frontier inference performance on AMD GPUs.

You will work at the intersection of inference systems, kernels, compilers, and hardware architecture, focusing on attention, GEMM, sampling, KV cache, and communication-heavy paths to enhance speed, reliability, and

Qualifications

• Bachelor's degree or equivalent experience in computer science, engineering, systems, machine learning, or similar.
• Hands-on experience optimizing AMD GPU workloads using ROCm, HIP, Triton, CK, AITER, or similar AMD ecosystem tools.
• Deep understanding of AMD GPU execution, memory behavior, toolchains, kernel performance, and backend-specific performance constraints.
• Experience optimizing ML kernels or inference paths such as attention, GEMM, sampling, KV cache, fused kernels, or communication-heavy runtime paths.
• Strong performance profiling and benchmarking skills, with the ability to use measurements, hardware counters, correctness tests, and reproducible benchmarks to guide optimization work.

Responsibilities

• Build and optimize AMD GPU backends, kernels, runtime paths, and benchmarking infrastructure for vLLM on AMD GPUs.
• Collaborate at the boundary of inference systems, kernels, compilers, and hardware architecture to improve performance-critical paths.
• Contribute to the usability, speed, benchmarking, and maintainability of AMD GPU support in vLLM.

Education

Bachelor's degree or equivalent

Tools

ROCm

HIP

Triton

CK

AITER

Job description

Inferact seeks an AMD GPU performance engineer to advance vLLM as a premier inference engine on AMD accelerators. You will build and optimize AMD GPU backends, kernels, runtime paths, and benchmarking infrastructure to deliver frontier inference performance on AMD GPUs.

You will work at the intersection of inference systems, kernels, compilers, and hardware architecture, focusing on attention, GEMM, sampling, KV cache, and communication-heavy paths to enhance speed, reliability, and