Remote CUDA GPU Software Engineer - High-Performance AI/HPC

Bright Vision Technologies; SOUTH PLAINFIELD (NJ); Remote; USD 100,000 - 175,000; Full time

Job summary

Bright Vision Technologies is seeking a GPU Software Engineer (CUDA) for a fully remote role in the United States. You will design high-performance CUDA kernels and optimize GPU workloads for AI and HPC applications.

The role requires 10+ years of GPU programming, deep CUDA expertise, and strong C++ skills, with collaboration across product and engineering teams to deliver production-quality performance improvements.

Qualifications

• Ten or more years of GPU programming and performance engineering.
• Deep expertise in CUDA C/C++ and GPU programming models.
• Strong understanding of modern GPU architectures, memory hierarchies, and execution models.
• Hands-on experience profiling and optimizing GPU workloads in production.
• Experience integrating custom kernels into ML frameworks.

Responsibilities

• Design and implement high-performance CUDA kernels for compute-intensive workloads across AI and HPC use cases.
• Profile and optimize GPU code using tools such as Nsight Systems, Nsight Compute, and CUDA profilers.
• Tune memory access patterns, occupancy, register usage, and shared memory utilization for peak performance.
• Develop highly optimized libraries for linear algebra, attention, and other ML primitives.
• Optimize multi-GPU and multi-node training using NCCL, RDMA, and high-performance networking.
• Implement custom operators and fused kernels in PyTorch, JAX, or Triton.
• Collaborate with ML engineers to identify performance bottlenecks in training and inference pipelines.
• Develop benchmarks and regression tests to safeguard performance over time.

Skills

CUDA programming

GPU performance engineering

C++

Profiling

Education

Bachelor's or Master's in CS/CE

Tools

NVIDIA Nsight

NCCL

MPI

CUDA profiling tools

Job description

Bright Vision Technologies is seeking a GPU Software Engineer (CUDA) for a fully remote role in the United States. You will design high-performance CUDA kernels and optimize GPU workloads for AI and HPC applications.

The role requires 10+ years of GPU programming, deep CUDA expertise, and strong C++ skills, with collaboration across product and engineering teams to deliver production-quality performance improvements.