Skip to main content
Mercor (via AI Gig Scout) logo

Trainium (NKI) Kernel Expert, AWS Neuron / ML Accelerator Evaluation (Remote, Contract, $70–$90/hr) — Mercor via AI Gig Scout

Mercor (via AI Gig Scout)
2 days ago
Contract
Remote
Worldwide
$70 - $90 USD hourly

Trainium (NKI) Kernel Expert — Mercor via AI Gig Scout

Pay: $70–$90/hr · Location: Remote (United States) · Type: Contract

Full listing and apply link: https://aigigscout.com/jobs/mercor/trainium-nki-kernel-expert-list-aaabodrl07cqmjvbgadldiz6?utm_source=kubernetesjobs&utm_medium=jobboard&utm_campaign=aigigscout_growth


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

Source: AI Gig Scout job page. Apply there for the original platform listing. Disclosure: posted by AI Gig Scout, an independent listing site (not Mercor); the apply link may be a referral link.