Remote CUDA GPU Software Engineer — High-Perf HPC

Socket.dev; Ann Arbor (MI); On-site; USD 80,000 - 107,000; Full time

Job summary

Bright Vision Technologies seeks a GPU Software Engineer (CUDA) to design and optimize high-performance GPU workloads for AI training, inference, and data processing. You will focus on extracting peak performance from modern GPUs and collaborating across product, design, and engineering teams.

The ideal candidate has deep CUDA expertise, strong C++ skills, and a proven track record of shipping production-grade GPU code. Remote U.S.

Qualifications

• Bachelor’s or Master’s degree in Computer Science, Computer Engineering, or related field.
• Six or more years of experience in 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 familiarity with modern systems programming practices.
• Solid grounding in linear algebra and numerical methods.
• Strong communication and collaboration skills with research and engineering teams.

Responsibilities

• Design and optimize compute-intensive workloads on modern accelerator hardware.
• Extract maximum performance from GPU platforms for AI training, inference, and high-throughput data processing.
• Collaborate with product, design, engineering, operations, and business stakeholders.
• Contribute to code reviews, design reviews, and mentorship of junior engineers.

Skills

CUDA C/C++

GPU programming

Performance engineering

NCCL

MPI

GPU architectures

C++

debugging/ profiling

Education

Bachelor’s or Master’s degree in CS/CE

Tools

Triton

CUTLASS

TensorRT

LLVM

Job description

Bright Vision Technologies seeks a GPU Software Engineer (CUDA) to design and optimize high-performance GPU workloads for AI training, inference, and data processing. You will focus on extracting peak performance from modern GPUs and collaborating across product, design, and engineering teams.

The ideal candidate has deep CUDA expertise, strong C++ skills, and a proven track record of shipping production-grade GPU code. Remote U.S.