Senior HPC & GPU Architect - Remote

Bright Vision Technologies; Oregon; Híbrido; USD 130.000 - 180.000; Jornada completa

Descripción de la vacante

Bright Vision Technologies is seeking a highly experienced Parallel Computing Engineer with 10+ years of HPC, GPU programming, and parallel computing to optimize AI, machine learning, and scientific workloads. The ideal candidate will possess deep expertise in CUDA, GPU architecture, distributed computing, performance optimization, and large-scale AI infrastructure, with a proven track record of designing HPC solutions for enterprise and research environments.

We offer a fully remote U.S.

Formación

• 10+ years of experience in GPU programming, HPC, or parallel computing.
• Expert-level CUDA C/C++, GPU architecture, and massively parallel programming techniques.
• Experience with NCCL, MPI, CUDA-aware MPI, and distributed GPU communication.
• Experience integrating custom GPU kernels into PyTorch, TensorFlow, JAX, or Triton.
• Experience with cloud platforms or large GPU clusters.
• Strong analytical, communication, collaboration, and leadership skills.

Responsabilidades

• Design, develop, and optimize CUDA kernels for AI, deep learning, and scientific computing applications.
• Profile and optimize GPU workloads using Nsight and CUDA Profiler.
• Optimize GPU memory, kernel execution, and multi-GPU scaling.
• Design scalable distributed training and inference architectures.
• Develop custom GPU operators for ML frameworks (PyTorch, TensorFlow, JAX, Triton).
• Improve training and inference performance for large language models and AI workloads.
• Collaborate with AI researchers and software architects to accelerate production AI apps.
• Build benchmarking frameworks, regression tests, and optimization pipelines.
• Evaluate new GPU technologies and accelerator architectures.
• Mentor engineers and provide technical leadership in GPU optimization.

Conocimientos

CUDA C/C++

GPU programming

HPC

Parallel computing

Performance profiling

Distributed training

Debugging

Educación

Bachelor’s or Master’s in CS/CE/EE

Herramientas

NCCL

MPI

CUDA-aware MPI

PyTorch

TensorFlow

Triton

CUDA Profiling

Descripción del empleo

Bright Vision Technologies is seeking a highly experienced Parallel Computing Engineer with 10+ years of HPC, GPU programming, and parallel computing to optimize AI, machine learning, and scientific workloads. The ideal candidate will possess deep expertise in CUDA, GPU architecture, distributed computing, performance optimization, and large-scale AI infrastructure, with a proven track record of designing HPC solutions for enterprise and research environments.

We offer a fully remote U.S.