GPU Kernel Developer - AI Trainer

Mercor; Chicago (IL); On-site; USD 120,000 - 180,000; Full time

Job summary

Mercor seeks a professional to evaluate GPU/accelerator kernel development tasks used in frontier AI model training and evaluation. You will assess numerical correctness, performance benchmarking fairness, task scoping, and compilation/runtime validity across diverse kernel types.

The role requires strong experience with CUDA/Triton/NKI/Pallas ecosystems, profilers, and common failure modes. You will deliver rubric-based written feedback to guide improvements.

Qualifications

• 3+ years developing, optimizing, or verifying GPU/kernel code in two or more frameworks.
• Strong understanding of numerical-correctness criteria and reference implementations.
• Experience with performance profiling and benchmarking tools.
• Familiarity with common kernel compilation/runtime failure modes.
• Experience with at least three kernel task types: generation, translation/lowering, migration, debugging, optimization, or fusion.

Responsibilities

• Evaluate kernel development tasks for correctness, performance, and completeness.
• Provide rubric-based written feedback on scope, correctness, and runtime behavior.

Skills

GPU kernels

CUDA

Triton

NKI/Pallas (JAX)

numerical correctness

performance profiling

benchmarking

kernel task types

Tools

Nsight

ncu

roofline analysis

Job description

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)