3 дня назад
AWS Trainium / Neuron Kernel Interface (NKI) Engineer
65$
Вакансия из Hirify Global, списка международных tech-компанийДля мэтча и отклика нужен Plus
Мэтч & Сопровод
Для мэтча с этой вакансией нужен Plus
Описание вакансии
Текст:
TL;DR
AWS Trainium / Neuron Kernel Interface (NKI) Engineer (AI infrastructure): Evaluating and optimizing low-level NKI kernels for AWS Trainium and Inferentia2 workloads with an accent on memory hierarchy, DMA scheduling, numerical correctness, and performance benchmarking. Focus on reviewing CUDA-to-NKI migrations, identifying Trainium-specific bottlenecks, and providing clear technical feedback on kernel implementations.
Location: Fully remote from Argentina, Brazil, Chile, Colombia, Ecuador, Mexico, Portugal, Spain, or Uruguay
Compensation: $65 per hour
Company
is running a specialized project focused on evaluating and improving kernel development tasks for AI workloads.
What you will do
- Review NKI kernel implementations for correctness, idiomatic development patterns, and Trainium optimization.
- Evaluate CUDA-to-NKI kernel migrations and cross-platform numerical correctness.
- Analyze performance bottlenecks and benchmark workloads on AWS Trainium.
- Assess memory management across SBUF, PSUM, and HBM.
- Review tile-based computation, DMA scheduling, and other Trainium-specific techniques.
- Provide clear written technical feedback and quality assessments.
Requirements
- 2+ years of hands-on experience developing or optimizing NKI kernels.
- Experience with AWS Trainium and/or Inferentia2 hardware.
- Strong understanding of tile-based computation, SBUF/PSUM/HBM memory hierarchy, partition dimension constraints, and DMA orchestration.
- Ability to evaluate CUDA-to-NKI migrations and understand numerical differences between GPU and Trainium backends.
- Experience profiling and optimizing Trainium workloads.
- Strong analytical and technical writing skills.
Nice to have
- Experience with the AWS Neuron SDK or Neuron Compiler.
- CUDA or Triton kernel development experience.
- Knowledge of NeuronCore-v2 architecture and FP32, BF16, FP8, or INT8 workloads.
- Experience benchmarking Trn1 or Trn2 instances.
- Familiarity with
nki.language,@nki.jit, or XLA custom calls.
Culture & Benefits
- Remote, part-time, project-based consulting engagement.
- Focus on technically challenging AI projects and low-level ML kernel optimization.
- Hourly compensation of $65.
Будьте осторожны: если работодатель просит войти в их систему, используя iCloud/Google, прислать код/пароль, запустить код/ПО, не делайте этого - это мошенники. Обязательно жмите "Пожаловаться" или пишите в поддержку. Подробнее в гайде →