Назад
Company hidden
3 месяца назад

AI Infrastructure Engineer

Формат работы
hybrid
Тип работы
fulltime
Грейд
middle
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 Infrastructure Engineer (AI/GPU): Building and scaling Meshy's AI inference infrastructure and model-serving platform with an accent on GPU resource management, orchestration, and production reliability. Focus on optimizing throughput and latency, implementing GPU virtualization, designing auto-scaling systems, and turning experimental models into observable and cost-efficient services.

Location: Beijing; hybrid work with remote and on-site options

Company

hirify.global develops generative AI technology that transforms text and images into 3D models for professional artists and hobbyists.

What you will do

  • Build and scale AI inference infrastructure, including model serving, scheduling, orchestration, and auto-scaling.
  • Design CPU and GPU resource management systems to improve utilization and cost efficiency.
  • Implement production-grade GPU scheduling, multiplexing, and virtualization using technologies such as MIG, MPS, and vGPU.
  • Optimize inference throughput, latency, and stability for high-concurrency business scenarios.
  • Contribute to reliability engineering, disaster recovery, observability, and cloud cost governance.
  • Develop AI-native infrastructure and automated operations to support business growth.

Requirements

  • 3–5 years of experience in backend or infrastructure engineering.
  • Strong proficiency in Go or Python and solid software engineering fundamentals.
  • Deep understanding of Linux internals, networking, and distributed systems.
  • Hands-on experience with Kubernetes, Docker, and microservices architecture.
  • Project experience in inference systems, task scheduling, or resource management.
  • Self-driven approach, fast learning ability, and willingness to take ownership in a startup environment.

Nice to have

  • Experience with GPU platforms or customized Kubernetes schedulers.
  • Familiarity with Ray, model-serving frameworks, or distributed inference architectures.
  • Experience with GPU multiplexing technologies such as MIG, MPS, or vGPU.
  • Background in SRE, observability, or cloud cost optimization.
  • Open-source contributions or significant technical influence in the community.

Culture & Benefits

  • Competitive salary, equity, and benefits package.
  • Flexible work environment with remote and on-site options.
  • Opportunities for rapid professional growth and development.
  • Inclusive culture focused on creativity, innovation, and collaboration.
  • Unlimited flexible time off, stock options for core team members, and comprehensive health, dental, and vision insurance.
  • 401(k) plan and modern office equipment.

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 →