Назад
Company hidden
8 часов назад

Principal Software Engineer (AI Virtualization)

127 100 - 226 000$
Формат работы
onsite
Тип работы
fulltime
Грейд
senior
Английский
b2
Страна
US
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

Principal Software Engineer (AI Virtualization): Developing and integrating an AI Virtualization Stack to provide hardware-agnostic acceleration for AI/ML workloads on Virtual Machines with an accent on ML compilation technologies and multi-vendor GPU/XPU support. Focus on optimizing PyTorch and JAX backends using OpenXLA and implementing LLM inference optimizations like KV-caching and FlashAttention.

Location: USA-CA - Promontory B. Must have legal authorization to work in the US

Salary: $127,100 - $226,000

Company

hirify.global is a global leader in semiconductor and infrastructure software solutions, with a focus on shaping the future of virtualization technology through its VMware subsidiary.

What you will do

  • Research, design, and develop the AI Virtualization Stack for the ESXi server product.
  • Implement and optimize PyTorch and JAX backends using the OpenXLA framework for high-performance AI/ML execution.
  • Re-architect performance-critical ML acceleration code, focusing on LLM inference optimizations such as KV-caching and FlashAttention.
  • Collaborate with virtual driver teams and external GPU/XPU vendors to provide end-to-end ML framework support.
  • Deliver high-quality software according to VCF coding guidelines and maintain detailed technical documentation.

Requirements

  • Bachelor's degree with 12+ years of experience or Master's degree with 10+ years of experience in a related field.
  • 5+ years of experience in ML framework/runtime development and GPU/XPU backend engineering.
  • Strong proficiency in C++ and Python programming languages.
  • Direct experience with ML frameworks (PyTorch, JAX) and graph/ML compiler technologies (e.g., OpenXLA).
  • Must have legal authorization to work in the US

Nice to have

  • Experience with inference servers such as vLLM or Triton.
  • Experience with low-level GPU kernel development (CUDA, ROCm, or similar).

Culture & Benefits

  • Competitive annual base salary with discretionary annual bonuses and equity awards.
  • Comprehensive medical, dental, and vision insurance plans.
  • 401(K) participation with company matching and Employee Stock Purchase Program (ESPP).
  • Paid sick leave, vacation time, and company paid holidays.
  • Support for diverse backgrounds as an equal opportunity employer.

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 →