6 gpu inference performance engineer jobs at 4 companies in Texas
1mo
Save
Mark Applied
Hide
Staff Engineer, Inference Optimizations
Austin or Seattle
$191k-$239k/yr RemoteFull Time
5+ YOE5+ years in high-performance computing or AI infrastructure with GPU architecture expertise, experience optimizing attention layers and distributed GPU kernels, and strong low-level systems design and open-source contributions.
AITER, CUDA, ROCm, TensorRT, OpenAI Triton
1mo
Save
Mark Applied
Hide
Senior Deep Learning Software Engineer, Inference
California or Texas or New York or Washington or Massachusetts
$152k-$288k/yr RemoteFull Time
5+ YOEMasters/PhD or equivalent,5+ years software development,excellent C/C++ skills,CUDA and GPU programming experience preferred,experience optimizing/deploying DL inference,Python and performance profiling experience helpful.
CUTLASS, OAI Triton, NCCL, CUDA, vLLM, SGLang, FlashInfer, PyTorch, NVSHMEM, C/C++, Python
2w
Save
Mark Applied
Hide
Engineering Manager, Deep Learning Inference
Santa Clara or Washington or Texas or New York or Washington or Massachusetts
$184k-$357k/yr RemoteFull Time
6+ YOE3+ MgmtRequires MS, PhD, or equivalent experience; 6+ years software development; 3+ years technical leadership or engineering management; C/C++, GPU programming, performance optimization, and production deep learning deployment.
vLLM, SGLang, FlashInfer, CUDA, Triton, CUTLASS, NIXL, NCCL, NVSHMEM, C/C++, Python, PyTorch, TensorRT-LLM, Agile
2w
Save
Mark Applied
Hide
Research Kernel Engineer
Singapore or Austin
OnsiteFull Time
Requires a degree in computer science, electrical engineering, or related field; CUDA or Triton, Python, C++, GPU architecture, profiling, inference optimization, and high-performance computing experience.
CUDA, Triton, Python, C++, Nsight Compute, Nsight Systems, vLLM, SGLang, TensorRT-LLM, MLIR, TVM, TorchInductor
2mo
Save
Mark Applied
Hide
Senior Deep Learning Framework Communications Engineer
Santa Clara or Austin or Westford or Durham or United States
$152k-$288k/yr HybridFull Time
5+ YOE5+ years software engineering experience in HPC/AI, experience with PyTorch/JAX and inference engines, Python/C++/CUDA development, performance benchmarking and profilers, understanding of multi-GPU communication and compilers.
PyTorch, TRT-LLM, vLLM, SGLang, JAX, NCCL, NVSHMEM, GPUDirect, torch.compile, PyTorch profiler, NVIDIA Nsight Systems, Python, C++, CUDA, Triton, cuTe, MPI
3mo
Save
Mark Applied
Hide
Software Solutions Architect
Austin or Boxborough or Markham
$212k-$318k/yr OnsiteFull Time
Architect and deliver enterprise software solutions leveraging AMD GPUs/APUs; engage customers and partners; strong software engineering, AI inference stack and performance optimization experience.
ROCm, ONNX Runtime, ONNX, PyTorch, TensorRT, CUDA, Docker, Kubernetes, C, C++, Python