Kernel Performance Engineer – GPU AI Inference

INFERACT SINGAPORE PTE. LTD.

Singapore

On-site

SGD 167,000 - 335,000

Full time

10 days ago
Application generator

Turn this role into an interview — a resume and cover letter built around what this employer wants.

Get past ATS filters

Benefits offered by this job

Equity
Medical, dental, vision

Job summary

Inferact Singapore PTE. LTD. seeks a performance engineer to squeeze every FLOP from modern accelerators and write kernels and low-level optimizations for vLLM. You will ensure compatibility across NVIDIA GPUs and emerging silicon, collaborating with hardware teams to push peak throughput.

The role requires deep CUDA experience, strong C++/Python skills, and expertise in profiling tools. Fresh grads welcome; equity is offered along with medical, dental, and vision benefits.

Qualifications

  • Bachelor's degree or equivalent in CS/Engineering or similar.
  • Deep experience writing CUDA kernels or equivalent (CuTeDSL, Triton, TileLang, Pallas).
  • Strong understanding of GPU architecture: memory hierarchy, warp scheduling, tiling, tensor cores.
  • Proficiency in C++ and Python with ability to write high-performance code.
  • Experience with profiling tools (Nsight, rocprof) and performance optimization methodologies.
  • Obsession with benchmarks and squeezing every percentage point of speedup.

Responsibilities

  • Write kernels and low-level optimizations for vLLM to maximize performance across accelerator types.
  • Collaborate with hardware vendors to extract maximum throughput on new chips.
  • Develop portable, high-performance C++/Python code and profiling workflows.

Skills

CUDA kernels
GPU architecture
C++
Python
Nsight/rocprof
benchmarking
performance optimization

Education

Bachelor's degree in CS/Engineering

Tools

CuTeDSL
Triton
TileLang
Pallas

Job description

Inferact Singapore PTE. LTD. seeks a performance engineer to squeeze every FLOP from modern accelerators and write kernels and low-level optimizations for vLLM. You will ensure compatibility across NVIDIA GPUs and emerging silicon, collaborating with hardware teams to push peak throughput.

The role requires deep CUDA experience, strong C++/Python skills, and expertise in profiling tools. Fresh grads welcome; equity is offered along with medical, dental, and vision benefits.

Get your free, confidential resume review.

or drag and drop your file here.

Similar jobs

Similar jobs worth comparing

Member of Technical Staff, Kernel Engineering
Member of Technical Staff, Kernel Engineering

INFERACT SINGAPORE PTE. LTD. • Singapore

On-site
SGD 167,000 - 335,000
Equity
Medical, dental, vision
AMD GPU Inference Performance Engineer
AMD GPU Inference Performance Engineer

INFERACT SINGAPORE PTE. LTD. • Singapore

On-site
SGD 167,000 - 335,000
Equity
Medical insurance
Dental
Member of Technical Staff, AMD GPU Performance Engineering
Member of Technical Staff, AMD GPU Performance Engineering

Inferact • Singapore

On-site
SGD 200,000 - 400,000
Medical coverage
Dental coverage
Vision coverage
+1
GPU Compute Infrastructure Engineer
GPU Compute Infrastructure Engineer

INFERACT SINGAPORE PTE. LTD. • Singapore

On-site
SGD 167,000 - 335,000
Equity
Medical, dental, and vision coverage
TPU Performance Engineer for Cutting-Edge Inference
TPU Performance Engineer for Cutting-Edge Inference

INFERACT SINGAPORE PTE. LTD. • Singapore

On-site
SGD 167,000 - 335,000
Medical coverage
Dental coverage
Vision coverage
+1
Member of Technical Staff, AMD GPU Performance Engineering
Member of Technical Staff, AMD GPU Performance Engineering

INFERACT SINGAPORE PTE. LTD. • Singapore

On-site
SGD 167,000 - 335,000
Equity
Medical insurance
Dental
GPU Compute Cluster Engineer
GPU Compute Cluster Engineer

Inferact • Singapore

On-site
SGD 200,000 - 400,000
Medical coverage
Dental coverage
Vision coverage
+1
Member of Technical Staff, TPU Performance Engineering
Member of Technical Staff, TPU Performance Engineering

Inferact • Singapore

On-site
SGD 200,000 - 400,000
Medical, dental, and vision coverage
Equity options
AI GPU Infra Engineer — Scale High-Performance Compute
AI GPU Infra Engineer — Scale High-Performance Compute

Hamilton Barnes Associates Limited • Singapore

On-site
SGD 180,000 - 220,000
Comprehensive health, dental, and vision insurance
401(k) with employer matching
Equity options
+1
TPU Inference Performance Engineer
TPU Inference Performance Engineer

Inferact • Singapore

On-site
SGD 200,000 - 400,000
Medical, dental, and vision coverage
Equity options