hiringremote.Get free job alerts

Trainium (NKI) Kernel Expert

$70–90/hr · AI expert network · remote, 40 hrs/week

Open to people living in the United States.

Check history

CheckedStatusSlots leftChangeHow
14 Nov 2026Open30Script, platform’s board
13 Nov 2026Open30Script, platform’s board
12 Nov 2026Open30Script, platform’s board
11 Nov 2026Open30Script, platform’s board
10 Nov 2026Open30Script, platform’s board
9 Nov 2026Open30Script, platform’s board
8 Nov 2026Open30Script, platform’s board
7 Nov 2026Open30Script, platform’s board
6 Nov 2026Open30Script, platform’s board
5 Nov 2026Open3–Script, platform’s board

The script reads the platform’s own job board every night. A job not confirmed for 10 days comes off the list.

An older role: first posted 81d ago, and AI expert network still listed it when it was last checked on 14 Nov 2026. Newer roles tend to fill faster. See the jobs hiring now.

What the work is

Evaluate the quality, correctness, and hardware-appropriateness of Neuron Kernel Interface (NKI) development tasks used to train and evaluate a frontier AI lab's models. You'll assess CUDA→NKI migration fidelity, Trainium-specific performance-optimization quality, and cross-platform numerical-correctness standards — and provide clear, rubric-based written feedback.

Basic Qualifications

  • 2+ years of hands-on experience developing or optimizing kernels using the Neuron Kernel Interface (NKI) targeting AWS Trainium/Inferentia2 hardware
  • Strong understanding of NKI-specific development patterns: tile-based computation, SBUF/PSUM/HBM memory-hierarchy management, partition-dimension constraints, and DMA orchestration
  • Demonstrated experience assessing CUDA→NKI migration quality
  • Familiarity with Trainium-specific performance profiling (NeuronCore pipeline utilization, tensor-engine throughput, memory-bandwidth bottlenecks)
  • Experience defining or evaluating cross-platform numerical-correctness standards (GPU vs Trainium accumulation order, rounding behavior, mixed-precision semantics)

Preferred Qualifications

  • Direct experience with AWS Neuron SDK, Neuron Compiler internals, or contributions to NKI kernel libraries
  • Prior CUDA or Triton kernel development
  • Familiarity with Trainium hardware specifications (NeuronCore-v2 architecture, on-chip SRAM topology, supported data types: FP32/BF16/FP8/INT8)
  • Experience benchmarking ML training workloads on Trn1/Trn2 instances

The platform posted this on 25 Aug 2026.

Similar jobs hiring now

Open the full list
  1. –Generalist Expert$40–70/hrAI expert networkno degreeUS, CA, UK +1US, CA, UK +1Checked auto, 14 Nov
  2. Posted 12 NovChip Design Expert (RTL Design & Verification)$100/hrAI expert network17 slots leftUS, CA, UK +1US, CA, UK +1Checked auto, 14 Nov
  3. Posted 11 NovFab Safety and Emergency Response Expert$85/hrAI expert network21 slots leftUS, CA, UK +1US, CA, UK +1Checked auto, 14 Nov
  4. Posted 9 NovFab Safety and Emergency Response Expert (Japanese)$85/hrAI expert network19 slots leftUS, CA, UK +1US, CA, UK +1Checked auto, 14 Nov
  5. Posted 5 NovCivil Engineer Reviewer$90/hrAI expert network5 slots leftUS, CA, UK +1US, CA, UK +1Checked auto, 14 Nov
  6. Posted 5 NovMechanical Engineer Reviewer$90/hrAI expert network7 slots leftUS, CA, UK +1US, CA, UK +1Checked auto, 14 Nov
  7. Posted 5 NovElectrical Engineering Writer$80/hrAI expert network33 slots leftUS, CA, UK +1US, CA, UK +1Checked auto, 14 Nov
  8. Posted 5 NovElectrical Engineer Reviewer$90/hrAI expert network3 slots leftUS, CA, UK +1US, CA, UK +1Checked auto, 14 Nov