For companies: explore licensing operational data for AI. Check eligibility

GPU Kernel Expert

$70–$90/hr

Apply on Mercor →

New to Mercor? before applying.

Get new roles by emailFollow on X

Jobs › Software Engineering › Mercor

Pay
$70 to $90 per hour
Pay type
Hourly
Platform
Mercor
Field
Software Engineering
Where
Remote, for applicants in United States
First seen
Posted
History
Half of Mercor roles listed since Oct 2 were gone within 28 days (of 329). How long roles stay open
Feed read

This listing comes from Mercor's own public job feed. The posting on Mercor is the source of truth.

About the 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)

More: Every role for software engineers · Roles open in United States · How Mercor pays, in its own words · What AI training roles pay · Free resume help