NKI Kernel Optimization Specialist

Mercor; San Francisco (CA); On-site; USD 120,000 - 180,000; Full time

Job summary

Mercor is seeking a specialist to 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 will assess CUDA→NKI migration fidelity, Trainium-specific performance, cross-platform numerical-correctness standards, and provide rubric-based written feedback.

Reporting into Mercor's AI systems group, you will work with kernel engineers and ML developers to ensure robust hardware-aware

Qualifications

• 2+ years hands-on kernel development with NKI targeting Trainium/Inferentia2.
• Expertise in NKI patterns: tile-based computation, SBUF/PSUM/HBM memory hierarchy, DMA.
• Experience assessing CUDA→NKI migration quality and Trainium profiling.

Responsibilities

• Evaluate quality, correctness, and hardware-appropriateness of NKI development tasks.
• Provide rubric-based written feedback on migration fidelity and performance.

Skills

NKI kernel development

CUDA to NKI migration

Trainium hardware

Tile-based computation

Memory hierarchy management

DMA orchestration

Performance profiling

Numerical correctness standards

Tools

AWS Neuron SDK

Neuron Compiler

NKI libraries

Job description

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