Remote GPU Kernel Engineer: CUDA/Triton Optimization

anyone-ai; United States; On-site; USD 138,000 - 248,000; Part time

Job summary

Anyone AI is recruiting experienced GPU Kernel Engineers for a remote, part-time, project-based consulting engagement focused on reviewing, debugging, and evaluating AI compute kernels.

You’ll work on CUDA/Triton kernels, assess numerical correctness, performance, and memory usage, and provide actionable feedback to optimize for target hardware, including translation between frameworks and hardware migrations, with emphasis on reproducibility and benchmarking.

Qualifications

• 3+ years of hands-on experience developing, optimizing, or debugging GPU/accelerator kernels.
• Strong understanding of GPU performance optimization.
• Experience with kernel profiling tools such as Nsight, NCU, roofline analysis, or framework-native profilers.
• Understanding of floating-point numerical correctness and tolerance thresholds.
• Experience debugging kernel compilation and runtime issues.
• Ability to distinguish software defects, environment problems, and genuine optimization challenges.

Responsibilities

• Reviewing GPU and accelerator kernel implementations for correctness.
• Comparing outputs against reference implementations.
• Evaluating numerical tolerance thresholds.
• Reviewing kernel benchmarks and determining whether comparisons are fair.
• Identifying performance bottlenecks and optimization opportunities.
• Assessing whether performance targets are realistic given hardware limits.
• Reviewing kernel translations and hardware migrations.
• Identifying compilation, memory, and runtime issues.
• Providing clear, actionable technical feedback.

Skills

GPU kernel development

Kernel optimization

Kernel debugging

GPU performance analysis

Profiling tools experience

Numerical correctness

Tools

Nsight

NCU

Roofline analysis

Framework profilers

Triton

Pallas

Job description

Anyone AI is recruiting experienced GPU Kernel Engineers for a remote, part-time, project-based consulting engagement focused on reviewing, debugging, and evaluating AI compute kernels.

You’ll work on CUDA/Triton kernels, assess numerical correctness, performance, and memory usage, and provide actionable feedback to optimize for target hardware, including translation between frameworks and hardware migrations, with emphasis on reproducibility and benchmarking.