Remote CUDA GPU Engineer for High-Performance ML

Bright Vision Technologies; Monroeville (Allegheny County); Remote; USD 100,000 - 175,000; Full time

Job summary

Bright Vision Technologies is seeking a GPU Software Engineer (CUDA) to design and optimize compute-intensive workloads on modern accelerator hardware. You will work on AI training, inference, scientific computing, and high-throughput data processing, delivering measurable performance improvements.

The role requires deep CUDA expertise, collaboration across product and engineering teams, and a track record of shipping performant GPU software in production environments.

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.

Responsibilities

• Design and implement high-performance CUDA kernels for compute-intensive workloads across AI and HPC use cases.
• Profile and optimize GPU code using Nsight systems 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 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.
• Evaluate new GPU architectures and feature sets; advise on adoption strategy.
• Contribute to compiler-level optimizations for tensor programs with MLIR/LLVM.

Skills

CUDA C/C++

GPU performance

Profiling

NCCL

MPI

C++ systems

Education

Bachelor's or Master’s degree

Tools

Nsight Systems

Nsight Compute

CUDA profilers

Triton

CUTLASS

TensorRT

Job description

Bright Vision Technologies is seeking a GPU Software Engineer (CUDA) to design and optimize compute-intensive workloads on modern accelerator hardware. You will work on AI training, inference, scientific computing, and high-throughput data processing, delivering measurable performance improvements.

The role requires deep CUDA expertise, collaboration across product and engineering teams, and a track record of shipping performant GPU software in production environments.