GPU Kernel Expert
About this role
Evaluate the quality, correctness, and completeness of GPU/accelerator kernel development tasks used to train and evaluate a frontier AI lab's models. You'll assess numerical correctness, performance-benchmarking fairness, task scoping, and compilation/runtime validity across diverse kernel task types, and provide clear, rubric-based written feedback.
Basic Qualifications
- 3+ years of hands-on experience developing, optimizing, or verifying GPU/accelerator kernels in at least two of: CUDA, Triton, NKI, or Pallas (JAX)
- Strong understanding of numerical-correctness criteria for kernels (absolute/relative/ULP tolerances, reference-implementation selection)
- Demonstrated experience with performance profiling and benchmarking (nsight, ncu, roofline analysis, or framework-native profilers)
- Familiarity with common compilation and runtime failure modes (driver mismatches, OOM, launch-configuration errors, shape/stride mismatches, autotuning failures)
- Experience with at least three kernel task types: generation from specification, translation/lowering across frameworks, migration between hardware targets, debugging, performance optimization, or operator fusion
Preferred Qualifications
- Experience across both NVIDIA GPU (CUDA/Triton) and custom-accelerator (NKI/Pallas/TPU) ecosystems
- Background in compiler engineering, MLIR, or intermediate-representation lowering
- Understanding of memory-hierarchy optimization (shared-memory tiling, register pressure, bank conflicts, coalescing patterns)
- Contributions to kernel libraries (cuBLAS, cuDNN, Triton community kernels, JAX/XLA custom calls)
Details
- Pay: $70 to $90/hr
- Company: Mercor
- Location: Remote
- Eligible locations: United States
- Platform: Mercor
Frequently asked questions
How much does the GPU Kernel Expert role pay?
Mercor lists this GPU Kernel Expert position at $70 to $90/hr. Pay is set by Mercor and your exact offer depends on your experience and the scope of the work.
Is the GPU Kernel Expert role remote, and can I work from home?
Yes. Mercor lists this GPU Kernel Expert position as fully remote, so you can work from home or anywhere with a reliable computer and internet connection.
Is GPU Kernel Expert full time or part time?
Mercor lists this as a contractor remote role. Full details are in the role description above.
Which countries can apply for GPU Kernel Expert?
Mercor lists eligibility for United States. Check the Mercor listing for current requirements before applying.
Do I need experience to apply for GPU Kernel Expert?
The requirements are listed in the role description above. Mercor screens applicants through its own process, and relevant skills or credentials strengthen your application.
How do I apply for the GPU Kernel Expert role, and is it legit?
Use the apply button on this page to go straight to the official Mercor listing. Mercor is a real hiring marketplace and applying is free. No legitimate employer charges you to apply.
Stay Updated on Roles Like This
Subscribe to receive fresh openings aligned with AI Training & Evaluation and AI training roles across Mercor and JobHub by NeonLabs