{"html":"<p>Evaluate the quality, correctness, and hardware-appropriateness of Neuron Kernel Interface (NKI) development tasks used to train and evaluate a frontier AI lab&#39;s models. You&#39;ll assess CUDA→NKI migration fidelity, Trainium-specific performance-optimization quality, and cross-platform numerical-correctness standards — and provide clear, rubric-based written feedback.</p>\n<p>Basic Qualifications\n• 2+ years of hands-on experience developing or optimizing kernels using the Neuron Kernel Interface (NKI) targeting AWS Trainium/Inferentia2 hardware\n• Strong understanding of NKI-specific development patterns: tile-based computation, SBUF/PSUM/HBM memory-hierarchy management, partition-dimension constraints, and DMA orchestration\n• Demonstrated experience assessing CUDA→NKI migration quality\n• Familiarity with Trainium-specific performance profiling (NeuronCore pipeline utilization, tensor-engine throughput, memory-bandwidth bottlenecks)\n• Experience defining or evaluating cross-platform numerical-correctness standards (GPU vs Trainium accumulation order, rounding behavior, mixed-precision semantics)</p>\n<p>Preferred Qualifications\n• Direct experience with AWS Neuron SDK, Neuron Compiler internals, or contributions to NKI kernel libraries\n• Prior CUDA or Triton kernel development\n• Familiarity with Trainium hardware specifications (NeuronCore-v2 architecture, on-chip SRAM topology, supported data types: FP32/BF16/FP8/INT8)\n• Experience benchmarking ML training workloads on Trn1/Trn2 instances</p>"}