GPU Kernel Performance Engineer — Optimize & Benchmark

Acceler8

California

On-site

USD 140,000 - 240,000

Full time

2 days ago
Be an early applicant

Get a reply from this recruiter

Your resume and cover letter, tailored to exactly what they’re hiring for.

Get past ATS filters

Job summary

Acceler8 Talent is partnering with an early-stage AI company in Mountain View to hire a GPU Kernel Performance Engineer. You will profile workloads, optimize kernels, and connect low-level GPU work to system-wide performance improvements.

You will work across kernels, runtimes, and model execution, collaborating with serving infrastructure and ML teams to translate kernel improvements into real-world throughput gains.

Qualifications

  • Experience modifying GPU kernels and explaining bottlenecks and results.
  • Hands-on CUDA or comparable GPU/HPC experience.
  • Strong fundamentals in engineering and GPU architecture.
  • Open to early-career engineers or graduates.

Responsibilities

  • Profile GPU workloads to identify bottlenecks in compute, memory, synchronization, and communication.
  • Optimize existing kernels and develop new kernels where needed.
  • Investigate kernel fusion, memory movement, occupancy, and parallel execution.
  • Build reproducible benchmarks and verify numerical correctness.
  • Collaborate with serving infrastructure and ML teams to translate kernel improvements into workload performance gains.

Skills

GPU kernel optimization
CUDA programming
GPU architecture understanding
Performance analysis

Tools

Triton
CUTLASS
cuDNN
PTX/SASS
Nsight
NCCL
NVLink
NVSwitch
ROCm/HIP
XLA/TPU
Tensor Cores

Job description

Acceler8 Talent is partnering with an early-stage AI company in Mountain View to hire a GPU Kernel Performance Engineer. You will profile workloads, optimize kernels, and connect low-level GPU work to system-wide performance improvements.

You will work across kernels, runtimes, and model execution, collaborating with serving infrastructure and ML teams to translate kernel improvements into real-world throughput gains.

Get your free, confidential resume review.

or drag and drop your file here.

Similar jobs

Similar jobs worth comparing

GPU Kernel Optimization Engineer
GPU Kernel Optimization Engineer

Acceler8 Talent • Palo Alto (CA)

On-site
USD 180,000 - 240,000
GPU Kernel Performance Engineer
GPU Kernel Performance Engineer

Acceler8 Talent • Mountain View (CA)

On-site
USD 180,000 - 260,000
Onsite GPU Kernel Performance Engineer
Onsite GPU Kernel Performance Engineer

Acceler8 • San Francisco (CA)

On-site
USD 140,000 - 220,000
GPU Kernel Performance Engineer
GPU Kernel Performance Engineer

Acceler8 • San Francisco (CA)

On-site
USD 140,000 - 220,000
CUDA Kernel Performance Engineer
CUDA Kernel Performance Engineer

Acceler8 Talent • San Francisco (CA)

On-site
USD 150,000 - 190,000
GPU Kernel Performance Engineer — HPC/AI Infrastructure
GPU Kernel Performance Engineer — HPC/AI Infrastructure

Designworks Talent • Bellevue (WA)

Hybrid
USD 140,000 - 190,000
Performance Engineer
Performance Engineer

Acceler8 • California

On-site
USD 140,000 - 240,000
GPU/Kernel Engineer
GPU/Kernel Engineer

Acceler8 Talent • Palo Alto (CA)

On-site
USD 180,000 - 240,000
GPU Kernel Engineer - High-Performance ML Acceleration
GPU Kernel Engineer - High-Performance ML Acceleration

Baseten • Seattle (WA)

On-site
USD 180,000 - 360,000
Performance Engineer
Performance Engineer

Acceler8 Talent • Mountain View (CA)

On-site
USD 180,000 - 260,000