CUDA GPU Kernel Optimization Engineer

The work

You will optimize GPU kernels to improve computational throughput on modern hardware. The work includes profiling performance, finding bottlenecks, and recommending focused changes.

You will also improve C++ and CUDA code, develop GLSL and WebGPU shader workflows, document your findings, and help evaluate GPU performance approaches through measurable results.

• Analyze, profile, and optimize GPU kernels.
• Identify kernel bottlenecks and recommend optimization strategies.
• Refactor C++ and CUDA code for efficiency, maintainability, and use across GPU architectures.
• Implement GLSL and WebGPU graphics or compute shader logic.
• Write clear technical reports covering optimization steps and performance improvements.
• Contribute to design discussions and evaluate GPU performance metrics.
• Track developments in GPU programming and share useful technical insights.

What it pays and takes

This is a remote, part-time contractor role. The listing is marked entry level, but the work requires demonstrated GPU programming and performance-engineering expertise.

English is required. The role is available in the countries listed for this posting.

• Pay: $60-$100 per hour.
• Time: 20 or more hours per week.
• Work type: Remote contractor and part-time.
• Language: English.
• Required: CUDA programming and GPU kernel performance tuning.
• Required: Advanced C++ development in high-performance computing environments.
• Required: Hands-on GLSL and WebGPU experience for graphics or compute shaders.
• Required: Experience with Nsight, Visual Profiler, or comparable GPU profiling tools.
• Required: Strong analysis of kernel performance across hardware generations.
• Required: Clear written and verbal technical communication.
• Helpful: Experience working remotely with cross-disciplinary teams.
• Prior AI experience is not required.

How it works

Apply on OpenTrain with your resume, then complete the application on the hiring site.

About AI training work

AI training work uses human expertise to build and evaluate the code, examples, and feedback that help AI systems perform better. OpenTrain hires and contracts contributors for this work, and experienced technical specialists help assess and improve the systems behind modern AI tools.