Назад
Company hidden
6 дней назад

Software Engineer, GPU Performance (AI)

Формат работы
onsite
Тип работы
fulltime
Английский
b2
Страна
Singapore/US/Canada
Вакансия из списка Hirify.GlobalВакансия из Hirify Global, списка международных tech-компаний
Для мэтча и отклика нужен Plus

Мэтч & Сопровод

Для мэтча с этой вакансией нужен Plus

Описание вакансии

Текст:
/
TL;DR
Software Engineer, GPU Performance (AI): Optimizing model execution and inference infrastructure for AI video applications with an accent on GPU profiling, latency, throughput, and cost efficiency. Focus on developing high-performance GPU kernels, improving batching and memory management, and building benchmarks that prevent performance regressions across video workloads.

Location: Los Angeles, Palo Alto, San Francisco, Toronto, or Singapore

Company

A visual storytelling technology company building AI applications for avatar creation, interactive video, and video translation.

What you will do

  • Profile GPU utilization, kernel execution, memory bandwidth, and CPU–GPU data movement using NVIDIA Nsight Systems, Nsight Compute, and PyTorch Profiler.
  • Identify and measure bottlenecks across model execution, preprocessing, and inference serving.
  • Improve latency, throughput, GPU utilization, and cost through batching, scheduling, and memory management.
  • Develop or integrate high-performance GPU kernels when existing implementations limit performance.
  • Build benchmarks and automated regression checks for representative video workloads.
  • Collaborate with AI researchers and infrastructure engineers to bring optimizations into production.

Requirements

  • Experience optimizing GPU-based AI workloads or high-performance computing systems.
  • Strong Python skills and experience with PyTorch or a similar machine learning framework.
  • Understanding of GPU hardware concepts including memory bandwidth, cache behavior, tensor cores, and CPU–GPU data movement.
  • Experience using profiling tools to connect hardware behavior with application bottlenecks and validate improvements.
  • Ability to turn performance experiments into reliable production changes and communicate tradeoffs clearly.

Nice to have

  • Experience with CUDA, Triton, or C++ GPU programming.
  • Experience optimizing video, image, audio, diffusion, or Transformer models.
  • Familiarity with multi-GPU inference, GPU interconnects, quantization, or large-scale model serving.
  • Experience building performance benchmarks or regression testing infrastructure.
  • Prior experience in a fast-paced technology environment.

Culture & Benefits

  • Competitive salary and benefits package.
  • Dynamic and inclusive work environment.
  • Opportunities for professional growth and advancement.
  • Collaborative culture focused on innovation and creativity.
  • Access to current technologies and tools.

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 →