ML Systems Engineer: GPU Kernels to Distributed Inference

TensorScale

San Francisco (CA)

On-site

USD 180,000 - 260,000

Full time

18 hours ago
Be an early applicant

Get a reply from this employer

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

Get past ATS filters

Job summary

TensorScale in the San Francisco Bay Area seeks a GPU systems engineer to optimize speed and efficiency from kernels to distributed inference engines. You will improve training and inference for image, video, and world-model workloads with hands-on CUDA and Triton work.

You will profile bottlenecks with Nsight, design scalable multi-GPU deployments, and build benchmarks to ensure gains persist in production. Strong PyTorch knowledge and onsite work in the Bay Area are required.

Qualifications

  • 1+ years in deep learning inference/training systems or HPC.
  • Proficiency in CUDA and GPU profiling (Nsight).
  • Strong systems instincts across GPU architecture and kernels.
  • Experience with distributed multi-GPU debugging/optimization.
  • Familiarity with PyTorch and performance-critical model execution.
  • Comfort working onsite in the Bay Area.

Responsibilities

  • Optimize system and GPU performance of training and inference for image, video, and world-model workloads.
  • Profile and remove bottlenecks at kernel, memory, system, and cluster levels (Nsight and related tooling).
  • Implement low-level optimizations in CUDA / Triton.
  • Design and improve distributed inference / training engines for diffusion models.
  • Own communication performance across GPUs and nodes: NCCL, RDMA / InfiniBand / RoCE, and disaggregated serving.
  • Build benchmarking and regression harnesses so performance gains stick in production.
  • Hardware-aware kernel, runtime, and model co-design.

Skills

CUDA kernel optimization
Distributed systems
GPU profiling
PyTorch
Nsight tools

Tools

CUDA
Triton
Nsight
NCCL
InfiniBand/RoCE

Job description

TensorScale in the San Francisco Bay Area seeks a GPU systems engineer to optimize speed and efficiency from kernels to distributed inference engines. You will improve training and inference for image, video, and world-model workloads with hands-on CUDA and Triton work.

You will profile bottlenecks with Nsight, design scalable multi-GPU deployments, and build benchmarks to ensure gains persist in production. Strong PyTorch knowledge and onsite work in the Bay Area are required.

Get your free, confidential resume review.

or drag and drop your file here.

Similar jobs

Similar jobs worth comparing

Staff ML Systems Engineer - GPU & Distributed Training
Staff ML Systems Engineer - GPU & Distributed Training

true-talent-solutions-partners • Menlo Park (CA)

On-site
USD 180,000 - 230,000
ML Systems Engineer - Accelerate GPU Training (Equity)
ML Systems Engineer - Accelerate GPU Training (Equity)

Digital Waffle • Menlo Park (CA)

On-site
USD 350,000 - 550,000
Equity
ML Systems Engineer — Accelerate GPU Inference & Training
ML Systems Engineer — Accelerate GPU Inference & Training

Aionia Group • Menlo Park (CA)

On-site
USD 150,000 - 210,000
Member of Technical Staff, ML Systems ML Systems
Member of Technical Staff, ML Systems ML Systems

TensorScale • San Francisco (CA)

On-site
USD 180,000 - 260,000
Member of Technical Staff, ML Systems
Member of Technical Staff, ML Systems

true-talent-solutions-partners • Menlo Park (CA)

On-site
USD 180,000 - 230,000
Machine Learning Systems Engineer
Machine Learning Systems Engineer

Digital Waffle • Menlo Park (CA)

On-site
USD 350,000 - 550,000
Equity
Inference Systems Engineer for Scalable GPU ML (Remote)
Inference Systems Engineer for Scalable GPU ML (Remote)

Prime Intellect, Inc. • United States

Remote
USD 180,000 - 240,000
Equity incentives
Visa sponsorship
Relocation assistance
+1
Senior GPU Kernel Engineer — Turbocharge Inference
Senior GPU Kernel Engineer — Turbocharge Inference

relace • San Francisco (CA)

On-site
USD 180,000 - 300,000
Real-Time GPU Optimization Engineer - Inference
Real-Time GPU Optimization Engineer - Inference

techire ai • San Francisco (CA)

On-site
USD 230,000 - 300,000
Remote Inference Systems Engineer — GPU/CUDA Focus
Remote Inference Systems Engineer — GPU/CUDA Focus

Undisclosed • United States

Remote
USD 200,000 - 300,000