Назад
Company hidden
обновлено 1 день назад

Principal Hardware Product Manager (PCIe Accelerators & Server Infrastructure)

200 000 - 250 000$
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 Hardware Product Manager (PCIe Accelerators & Server Infrastructure) (GPU/HPC hardware): Defining and delivering high-density PCIe accelerator cards and scalable 2U HPC server configurations with an accent on silicon-to-system execution, expandable memory, and native high-bandwidth networking. Focus on optimizing PCIe Gen 5/6 architectures, integrating RISC-V-controlled Linux subsystems, and balancing thermal, power, BOM, and deployment constraints through mass production.

Location: Sunnyvale, California, United States

Salary: $200,000–$250,000 per year in California

Company

hirify.global is a semiconductor startup building high-performance, energy-efficient graphics processors for content creation, immersive experiences, scientific simulation, and real-time path tracing.

What you will do

  • Own product requirements and the hardware roadmap for single- and dual-chiplet PCIe accelerator cards and multi-chip 2U rack-mounted server architectures.
  • Define the expandable memory strategy using onboard LPDDR5X and user-upgradable DDR5 SO-DIMM/DIMM slots, supporting up to 2.25 TB per server node.
  • Develop the roadmap for integrated 400GbE and 800GbE communication fabrics and native networking capabilities.
  • Coordinate firmware and platform teams on standalone Linux subsystems, embedded RISC-V control, BMC, and IPMI functionality.
  • Manage thermal and power trade-offs across 120W single-slot boards and 500W multi-chip server environments.
  • Drive execution from post-tape-out validation through system NPI, mass production, ODM/EMS delivery, component sourcing, BOM optimization, and manufacturing resilience.

Requirements

  • 5+ years defining or engineering high-performance PCIe add-in cards or complex server systems.
  • Deep understanding of PCIe Gen 5.0/6.0 electrical integrity, signal routing, and form-factor constraints.
  • Strong knowledge of DDR5, LPDDR5X, or HBM memory architectures and their impact on FP64 simulation and path-tracing performance.
  • Familiarity with RISC-V or ARM processors, Linux-based system architectures, and 400Gbps+ Ethernet or InfiniBand fabrics.
  • Experience taking complex silicon or hardware products from post-tape-out validation into full production.
  • BS/MS in Electrical Engineering, Computer Engineering, or a related hardware field; MBA experience is highly valued.

Nice to have

  • Experience with HPC accelerators, GPUs, or server motherboards for render farms and HPC centers.
  • Experience transitioning from x86/Arm host controllers to open architectures such as RISC-V.
  • Knowledge of mechanical and thermal constraints for dense, multi-slot accelerator boards in standard data-center racks.

Culture & Benefits

  • First-principles problem solving and a mission focused on reducing barriers to content creation and consumption.
  • Values include fearlessness, adaptability, and selfless collaboration.
  • Medical, dental, and vision premiums covered at 100%.
  • Stock options, 401(k) matching, and work-from-home hardware.
  • Inclusive workplace centered on professionalism, integrity, and respect.

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 →