Anyone Ai

AWS Trainium / NKI Kernel Expert

Argentina - Fully Remote. Posted 2 months ago

The role

You will review and evaluate technical tasks involving NKI kernel correctness and Trainium-specific development patterns. The work includes evaluating CUDA to NKI migrations, performance optimization, and memory management.

What you will do

  • Review and evaluate NKI kernel correctness and Trainium-specific development patterns
  • Evaluate CUDA to NKI kernel migrations
  • Perform Trainium performance optimization and benchmarking
  • Manage memory across SBUF, PSUM, and HBM
  • Handle tile-based computation and DMA scheduling
  • Check cross-platform numerical correctness between CUDA/Triton and NKI
  • Identify Trainium-specific performance bottlenecks and optimization opportunities
  • Provide technical feedback and quality assessment of kernel implementations

Required qualifications

  • 2+ years of hands-on experience developing or optimizing kernels with the Neuron Kernel Interface (NKI)
  • Experience working with AWS Trainium and/or Inferentia2
  • Strong understanding of tile-based computation
  • Strong understanding of SBUF / PSUM / HBM memory hierarchy
  • Strong understanding of partition dimension constraints
  • Strong understanding of DMA orchestration
  • Strong understanding of Trainium-specific optimization techniques
  • Ability to evaluate CUDA to NKI migrations
  • Experience profiling and optimizing workloads on Trainium
  • Understanding of numerical differences across GPU and Trainium backends
  • Strong ability to analyze complex technical implementations and provide clear written feedback

Nice to have

  • Experience with the AWS Neuron SDK or Neuron Compiler
  • CUDA or Triton kernel development experience
  • Knowledge of NeuronCore-v2 architecture
  • Experience with FP32, BF16, FP8, and INT8 workloads
  • Experience benchmarking workloads on Trn1 or Trn2 instances
  • Familiarity with nki.language, @nki.jit, or XLA custom calls
  • Experience with technical evaluation, AI/ML data projects, RLHF, or rubric-based assessment

About the company

Anyone AI is recruiting experienced AWS Trainium / Neuron Kernel Interface (NKI) engineers for a specialized project.