Remote CUDA Developer - High-Performance GPU Programmer

Bright Vision Technologies; United States; Remote; USD 85,000 - 110,000; Full time

Job summary

Bright Vision Technologies is seeking a CUDA Developer for a 100% remote, full-time direct W2 role based in the United States. The role focuses on CUDA programming, GPU architecture, and high-performance computing to optimize workloads for AI training, inference, and data processing on modern accelerator hardware.

The ideal candidate has deep CUDA C/C++, strong GPU architecture knowledge, and a track record of delivering performance improvements on production GPU systems.

Qualifications

• Bachelor’s or Master’s degree in Computer Science, Computer Engineering, or a related field.
• 6+ 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.
• Familiarity with NCCL, MPI, and high-performance interconnect technologies.
• Experience integrating custom kernels into ML frameworks.
• Strong C++ skills and modern systems programming practices.
• Solid grounding in linear algebra and numerical methods.
• Strong communication and collaboration skills with research and engineering teams.

Skills

CUDA programming

GPU performance engineering

CUDA C/C++

GPU architectures

Profiling GPU workloads

Interconnect techs (NCCL/MPI)

ML frameworks integration

C++ systems programming

Numerical methods / linear algebra

Communication & collaboration

Education

Bachelor’s or Master’s in CS/CE

Tools

NCCL

MPI

Triton

CUTLASS

TensorRT

Job description

Bright Vision Technologies is seeking a CUDA Developer for a 100% remote, full-time direct W2 role based in the United States. The role focuses on CUDA programming, GPU architecture, and high-performance computing to optimize workloads for AI training, inference, and data processing on modern accelerator hardware.

The ideal candidate has deep CUDA C/C++, strong GPU architecture knowledge, and a track record of delivering performance improvements on production GPU systems.