Remote GPU Kernel Expert for AI Training & Evaluation

mercor; United States; Remote; USD 96,000 - 124,000; Full time

Job summary

Mercor is seeking a GPU Kernel Expert for remote contract work to support AI research teams. You will evaluate GPU/accelerator kernels for training and evaluation, focusing on correctness and performance.

You will collaborate with researchers, review compile/runtime behavior, and provide rubric-based feedback. Requires 3+ years with CUDA/Triton/NKI/Pallas and strong profiling experience.

Qualifications

• 3+ years of experience with CUDA, Triton, NKI, or Pallas (JAX).
• Strong understanding of numerical-correctness criteria for kernels.
• Experience with performance profiling and benchmarking (e.g., nsight, ncu).
• Familiarity with common compilation and runtime failure modes.
• Experience with at least three kernel task types.

Responsibilities

• Evaluate the quality and correctness of GPU/accelerator kernel development tasks for training and evaluating AI models.
• Assess numerical correctness, performance-benchmarking fairness, and task scoping across diverse kernel task types.
• Review compilation and runtime validity, providing clear, rubric-based written feedback.
• Collaborate with AI research teams to improve model training and evaluation processes.
• Work independently and asynchronously to meet deadlines and enhance AI model performance.

Skills

CUDA

Triton

NKI

Pallas (JAX)

Performance profiling

Tools

nsight

ncu

Job description

Mercor is seeking a GPU Kernel Expert for remote contract work to support AI research teams. You will evaluate GPU/accelerator kernels for training and evaluation, focusing on correctness and performance.

You will collaborate with researchers, review compile/runtime behavior, and provide rubric-based feedback. Requires 3+ years with CUDA/Triton/NKI/Pallas and strong profiling experience.