AIWorkJobs
Mercor logoMercorPlatform listing

GPU Kernel Expert

Review GPU and accelerator kernel-development tasks that support training and evaluation of a frontier AI lab’s models. Judge numerical correctness, benchmark fairness, task scope, and compilation and runtime validity…

Remote · United States onlyHourly
Work arrangement
Remote
Eligibility
United States only
Engagement
Hourly
Compensation
$70–$90/hr
Specialty
AI Training
Weekly commitment
40 hours per week

About the role

Review GPU and accelerator kernel-development tasks that support training and evaluation of a frontier AI lab’s models. Judge numerical correctness, benchmark fairness, task scope, and compilation and runtime validity across varied kernel work. You’ll also write rubric-based feedback that explains your findings.

What you would do

  • Evaluate kernel tasks for numerical correctness, including tolerance choices and reference implementations.
  • Assess whether performance benchmarks compare kernels fairly.
  • Review task scope across different kernel-development types.
  • Check compilation and runtime validity, including failure modes such as driver mismatches, out-of-memory errors, launch-configuration errors, shape or stride mismatches, and autotuning failures.
  • Write clear feedback based on evaluation rubrics.

Requirements

  • At least 3 years of hands-on experience developing, optimizing, or verifying GPU or accelerator kernels.
  • Kernel experience in at least two of CUDA, Triton, NKI, or Pallas (JAX).
  • Strong knowledge of kernel numerical-correctness criteria, including absolute, relative, and ULP tolerances and reference-implementation selection.
  • Demonstrated experience with performance profiling and benchmarking using tools such as Nsight, ncu, roofline analysis, or framework-native profilers.
  • Familiarity with common compilation and runtime failures, including driver mismatches, OOM, launch-configuration errors, shape or stride mismatches, and autotuning failures.
  • Experience with at least three kernel task types: generation from a specification, translation or lowering across frameworks, migration between hardware targets, debugging, performance optimization, or operator fusion.

Preferred qualifications

The source marks these as preferred, not required.

  • Experience with both NVIDIA GPU ecosystems, including CUDA or Triton, and custom-accelerator ecosystems such as NKI, Pallas, or TPU.
  • Background in compiler engineering, MLIR, or intermediate-representation lowering.
  • Knowledge of memory-hierarchy optimization, including shared-memory tiling, register pressure, bank conflicts, and coalescing patterns.
  • Contributions to kernel libraries such as cuBLAS, cuDNN, Triton community kernels, or JAX/XLA custom calls.

Who should apply

GPU kernel specialists with at least 3 years of hands-on experience and expertise in two or more supported kernel technologies should consider this role. Applicants should also bring profiling experience and work across at least three kernel task types.

How applying works on Mercor

Create a profile, complete the role checklist and AI interview, then verify your identity before a project offer.

  1. Create an account and confirm your résumé.
  2. Complete the role checklist, written assessment, and AI interview where the listing requires them.
  3. Submit the application and wait for review or matching.
  4. Complete a work trial and identity verification before onboarding.

Typical timeline: The AI interview is about 20 minutes; work trials are often 4–6 hours; identity checks are usually minutes.

Paid steps: The work trial is paid.

Assessment and interview requirements vary by role. Check the checklist inside the specific listing.

Process checked Nov 19, 2026. AIWorkJobs does not submit applications or charge a fee. Read the full Mercor process and its official source on the Mercor page.

Skills mentioned by the source

  • cuda
  • triton
  • nki
  • pallas
  • jax
  • gpu kernels
  • accelerator kernels
  • kernel benchmarking
  • nsight
  • ncu
  • roofline analysis
  • numerical correctness
  • kernel profiling
  • operator fusion
  • autotuning

Specialty areas

Specialties come from the source platform’s category taxonomy and are used to filter the job index.

Listing reference: gpu-kernel-expert-pECa5L. Source: Mercor. If something here contradicts the source, the source controls. Report a correction.

Related roles

Other work on the index.

See more in this category

Mercor

Trainium (NKI) Kernel Expert

Review Neuron Kernel Interface (NKI) development work that supports training and evaluating frontier AI models. You will judge kernel correctness, CUDA-to-NKI migration fidelity, Trainium performance choices, and numerical consistency across GPU and Trainium hardware, then write clear feedback against defined rubrics. The work calls for hands-on NKI experience with AWS Trainium or Inferentia2.

Location and eligibility
Remote · United States only
Engagement type
Hourly
Compensation
$70–$90/hr
  • neuron kernel interface
  • aws trainium
  • aws inferentia2
AI trainingView job

AfterQuery

GPU Kernel and ML Systems Researcher (Research Coding Tasks)

AfterQuery offers remote contract work for researchers and research engineers with hands-on experience in ML systems and GPU kernels. You will create research coding tasks, review AI model outputs, and work with a project lead to maintain research quality. Each task stands on its own, and onboarding covers its scope and a worked example. The role has no fixed weekly schedule and pays $50 per hour through Stripe.

Location and eligibility
Remote · Eligibility not specified
Engagement type
Not specified
Compensation
$50/hr
  • ml systems
  • gpu kernels
  • research coding
Machine Learning & AIView job

Meridial by Invisible

Technical Task Auditor

Audit technical tasks used to train and evaluate AI systems as an independent contractor. You will focus on one specialty that matches your experience, such as GPU kernels, Kubernetes, machine learning, or application security. Your reviews will check task quality, reproducibility, tests, and evaluation criteria, and you will provide actionable feedback on any problems.

Location and eligibility
Remote · Eligibility not specified
Engagement type
Not specified
Compensation
$60/hr
  • gpu kernels
  • aws trainium
  • nki
Quality Assurance & TestingView job

Outlier · via Braintrust

Senior Systems & Hardware Experts - AI Benchmarking

Use your systems or hardware engineering experience to create difficult, clearly specified challenges for AI agents to solve in a Linux terminal. The project is task-based and expected to last a few weeks. Tasks average six to seven hours, with early submissions potentially taking longer. Earn up to $1,350 per task, with higher rates possible based on task quality and submission volume. Onboarding requires two courses, a graded assessment of about 90 minutes, and a live webinar.

Location and eligibility
Remote · Eligible in 25 countries
Engagement type
Contract
Compensation
$1,350 fixed
  • systems engineering
  • hardware engineering
  • linux
Hardware & Embedded SystemsView job