Remote Trainium Kernel Expert (NKI) – AI Performance

mercor; United States; Remote; USD 96,000 - 124,000; Full time

Job summary

Mercor is a remote contract role for a Trainium (NKI) Kernel Expert, focused on evaluating kernel development tasks for AI training models and ensuring CUDA→NKI migration fidelity and Trainium performance. You will collaborate with AI researchers to guarantee numerical correctness across datasets and optimize training workloads.

Ideal candidates have 2+ years in NKI kernel work, familiarity with AWS Neuron tooling, and a proven ability to work independently on ML training challenges.

Qualifications

• 2+ years of experience developing or optimizing kernels using NKI targeting AWS Trainium/Inferentia2 hardware.
• Strong understanding of NKI-specific development patterns and memory-hierarchy management.
• Experience assessing CUDA→NKI migration quality.
• Familiarity with Trainium-specific performance profiling.
• Experience defining or evaluating cross-platform numerical-correctness standards.

Responsibilities

• Evaluate the quality, correctness, and hardware-appropriateness of Neuron Kernel Interface (NKI) development tasks for training and evaluating AI models.
• Assess CUDA→NKI migration fidelity and Trainium-specific performance-optimization quality.
• Review cross-platform numerical-correctness standards and provide clear, rubric-based feedback.
• Collaborate with AI research teams to ensure consistency and coverage across datasets.
• Work independently and asynchronously to improve AI model performance .

Skills

NKI kernel development

AWS Trainium/Inferentia2 hardware

Memory hierarchy management

CUDA→NKI migration assessment

Performance profiling

Cross-platform numerical-correctness

Tools

AWS Neuron SDK

Neuron Compiler internals

NKI kernel libraries

Job description

Mercor is a remote contract role for a Trainium (NKI) Kernel Expert, focused on evaluating kernel development tasks for AI training models and ensuring CUDA→NKI migration fidelity and Trainium performance. You will collaborate with AI researchers to guarantee numerical correctness across datasets and optimize training workloads.

Ideal candidates have 2+ years in NKI kernel work, familiarity with AWS Neuron tooling, and a proven ability to work independently on ML training challenges.