Назад
Company hidden
9 дней назад

AI GPU Arch Perf Analysis Intern

Формат работы
onsite
Тип работы
fulltime
Грейд
trainee
Английский
b2
Страна
China
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
AI GPU Arch Perf Analysis Intern (AI/GPU Performance): Analyzing and optimizing GPU compute kernels for AI and numerical workloads while reproducing inference and training workloads for next-generation Intel GPU and AI accelerator validation with an accent on profiling, performance modeling, and hardware/software co-design. Focus on identifying compute, memory, and pipeline bottlenecks and translating workload-level insights into GPU architecture improvements.

Location: On-site in Beijing, China

Company

hirify.global's GPU Compute Architecture team develops and analyzes next-generation GPU and AI accelerator platforms through hardware/software co-design.

What you will do

  • Analyze and optimize GPU compute kernels for AI and numerical workloads, including GEMM, attention, and operator fusion.
  • Reproduce representative AI inference and training workloads for GPU IP validation.
  • Profile GPU performance and identify compute, memory, and pipeline bottlenecks.
  • Build performance profiles and models to understand architecture-level behavior.
  • Provide workload- and kernel-level insights supporting GPU architecture design and hardware/software co-design.

Requirements

  • Currently pursuing a Bachelor's, Master's, or PhD in Computer Science, Computer Engineering, Electrical Engineering, or a related technical field.
  • Proficiency in Python for analysis, experimentation, or tooling.
  • Solid understanding of AI fundamentals, including common models and algorithms.
  • Strong interest in GPU architecture, GPU programming, parallel computing, and performance optimization.
  • Basic knowledge of computer systems, including CPU/GPU architecture, memory systems, and performance analysis.

Nice to have

  • Experience with GPU kernels or programming models such as CUDA, OpenCL, SYCL, or Triton.
  • Exposure to performance optimization, compilers, or parallel computing through coursework, research, or internships.
  • Strong analytical and problem-solving skills, including the ability to reason from profiling data.
  • Interest in AI systems and infrastructure beyond model-level development.
  • Ability to work effectively in a collaborative, cross-functional engineering environment.

Culture & Benefits

  • Full-time student internship with on-site work in Beijing.
  • Collaborative, cross-functional engineering environment focused on GPU architecture and AI infrastructure.
  • Shift 1 working schedule in China.

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 →