GPU Kernel Expert
Evaluate the quality, correctness, and completeness of GPU/accelerator kernel development tasks used… Pay as listed: $70–$90/hr. Remote (United States).
- Pay (as listed on Mercor)
- $70–$90/hr · Hourly
- Commitment
- 40 hrs/week
- Location
- Remote · United States
- Languages
- English
- Category
- Coding
- Posted
- Aug 26, 2026
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)
How this role compares
This role’s top listed rate is $90/hr, above the $75/hr median for the 172 open Coding roles that list hourly pay (8 in 10 top out between $35 and $140/hr).
Across Mercor’s 344 roles with hourly pay, the median is $90/hr, so this one is the same as it.
302 Coding roles are open on this board, from 10 platforms:
- Turing (104)
- SME Careers (57)
- Mercor (55)
- micro1 (39)
- AfterQuery (33)
- Terac (9)
- Ethos (2)
- Handshake AI (1)
- Meridial (1)
- Outlier (1)
Mercor’s listings were last checked on Nov 22, 2026.
Apply on Mercor — this is a referral link; we may receive a reward if you’re hired, at no cost to you.
Listed on Mercor. Details can change, so confirm on Mercor before applying.
Similar roles
- Trainium (NKI) Kernel Expert — Mercor · $70–$90/hr
- GPU Programming Software Engineer — micro1 · $50–$120/hr
- Embedded Systems / Kernel Engineer — Mercor · $100–$150/hr
- ML Research Engineer — Inference & GPU Kernels — AfterQuery · $135/hr