AI Work Central
For you AlertsAlerts
Anyone AIOpen · Source checked

GPU Kernel Engineer - CUDA, Triton & Accelerator Performance

$65/hr

Listed rate, USDContractCoding9 countries

Free: we never charge you to search or apply. The button opens this role on Anyone AI's own site.

We may earn a referral fee if you join through this link. You pay nothing for it. · How we earn

Get roles that fit you by email. Free.

Email me roles that fit

Other open Coding roles

Each is open in at least one country this role lists. Newest first. See the full list

Can I apply from my country?

9 countries

  • Argentina
  • Brazil
  • Chile
  • Colombia
  • Ecuador
  • Mexico
  • Portugal
  • Spain
  • Uruguay

Key details

Location
Remote, in the countries above
Contract type
Contract
Language
English
Field
Coding
  1. Posted on Anyone AI
  2. Last checked

First seen over 2 weeks ago, last checked 15 Nov.

Entry: open · 54 roles today · checked 15 November 2026

In plain words

Who can apply
The listing is open to people in 9 countries, among them Argentina, Brazil, Chile, Colombia, Ecuador, Mexico and 3 more.
Pay and time
$65/hr as listed, contract work, remote.

What you'll do

Anyone AI is recruiting experienced GPU Kernel Engineers for a specialized project focused on reviewing, debugging, and evaluating high-performance compute kernels used in AI workloads.

We’re looking for engineers with hands-on experience writing and optimizing kernels across frameworks such as CUDA, Triton, NKI, or Pallas, with a strong understanding of numerical correctness, GPU performance, memory optimization, and benchmarking.

What You’ll Work On

You’ll work with GPU and accelerator kernel tasks involving:

  • Kernel implementation and debugging
  • CUDA and Triton optimization
  • Translation between kernel frameworks
  • Hardware migration
  • Operator fusion
  • Performance profiling and benchmarking
  • Numerical correctness verification
  • Compilation and runtime debugging
  • Memory hierarchy optimization
  • Kernel-level AI workload performance

You’ll assess whether implementations are technically correct, efficiently designed, reproducible, and appropriately optimized for the target hardware.

What We’re Looking For

  • 3+ years of hands-on experience developing, optimizing, or debugging GPU or accelerator kernels
  • Strong experience with at least two of the following:
  • CUDA
  • Triton
  • NKI / AWS Neuron
  • Pallas / JAX
  • Strong understanding of GPU performance optimization
  • Experience with kernel profiling tools such as Nsight, NCU, roofline analysis, or framework-native profilers
  • Understanding of:
  • Memory bandwidth
  • Compute throughput
  • GPU occupancy
  • Shared memory
  • Register pressure
  • Memory coalescing
  • Bank conflicts
  • Strong understanding of floating-point numerical correctness and tolerance thresholds
  • Experience debugging kernel compilation and runtime issues
  • Ability to distinguish software defects, environment problems, and genuine optimization challenges

Relevant Experience

Candidates should have experience with several of the following types of work:

  • Writing kernels from technical specifications
  • Translating kernels between CUDA, Triton, or other frameworks
  • Migrating kernels across hardware platforms
  • Debugging incorrect kernel implementations
  • Optimizing kernel performance
  • Fusing multiple operations into optimized kernels

Nice to Have

  • Experience across both NVIDIA GPU and custom accelerator ecosystems
  • Experience with AWS Trainium, TPU, JAX, or other accelerators
  • Compiler engineering experience
  • Familiarity with MLIR, XLA, or intermediate representation lowering
  • Contributions to GPU or ML kernel libraries
  • Experience with cuBLAS, cuDNN, Triton community kernels, or JAX/XLA custom calls
  • Experience with AI model evaluation, RLHF, or technical benchmark development

What You’ll Be Responsible For

  • Reviewing GPU and accelerator kernel implementations for correctness
  • Comparing outputs against reference implementations
  • Evaluating numerical tolerance thresholds
  • Reviewing kernel benchmarks and determining whether comparisons are fair
  • Identifying performance bottlenecks and optimization opportunities
  • Assessing whether performance targets are realistic given hardware limits
  • Reviewing kernel translations and hardware migrations
  • Identifying compilation, driver, memory, shape, and runtime issues
  • Determining whether technical tasks are genuinely difficult or incorrectly configured
  • Providing clear, actionable technical feedback

Engagement

Work Type: Remote

Engagement: Part-time, project-based consulting

Focus: GPU kernels, performance engineering, debugging, and technical evaluation

This role is ideal for engineers who enjoy working close to the hardware, optimizing GPU workloads, debugging low-level performance issues, and pushing AI compute systems toward their performance limits.

From the Anyone AI listing, as published.

How to apply

Software Engineering and Coding interview questions

Pay

Listed by Anyone AI, in USD. Is Anyone AI legit?

This role All Coding

On a ruler from $0 to $150 an hour: $65.

Compared with 149 Coding roles with an hourly rate: the median is $70 and half sit between $60 and $95. Midpoint of each listed range, 15 Nov.

Estimate a week at this rate

How this role compares

At $65 an hour (its listed rate), this role is $10 above the median Anyone AI role, $55 from 51 roles with an hourly rate and $5 below the median Coding role on all platforms, $70 from 149 roles. The medians are the count of our Pay Index on 15 November 2026, with each role counted once.

Entry at Anyone AI is open: its own job list had open roles when we read it on 15 November 2026.

Similar open roles: Ground Combat & Special Operations SME at micro1, $75 to $130/hr; Sr. Full-Stack Software Engineer at micro1, $50 to $100/hr; Subject Matter Experts: Machine Learning Model Evaluation at Terac, $75/hr.

Sign in or create an account

No password. The first time, this creates your account.

Continue with Google

Your account emails you up to 5 roles a week that fit your country and field. Don't send me emails

By creating an account you confirm you are 18 or over and accept the terms of use and the privacy notice. Who we are: legal notice.

Settings

Loading your settings