Назад
Company hidden
1 час назад

Chip Architect (Scale-up Ethernet Switch)

143 800 - 230 000$
Формат работы
onsite
Тип работы
fulltime
Грейд
senior
Английский
c1
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
Chip Architect (Scale-up Ethernet Switch) (ASIC/AI Networking): Defining switching architectures for next-generation Ethernet switches that interconnect datacenter-scale AI systems, from feature concepts and packet dataflows through silicon deployment and field debug, with an accent on traffic management, ASIC micro-architecture, and AI network workloads. Focus on designing implementable architectures, balancing power, performance, and area, and solving customer and hardware integration challenges across ingress and egress pipelines.

Location: San Jose, California, United States

Annual base salary: USD 143,800–230,000

Company

hirify.global develops XGS Ethernet switch products, including Tomahawk 6 and Tomahawk Ultra, for interconnecting datacenter-scale AI systems.

What you will do

  • Define switching architectures and new features for next-generation hirify.global XGS switches.
  • Design end-to-end dataflows across ingress and egress pipelines and traffic management blocks.
  • Write architecture specifications and present architectures to internal and external audiences.
  • Partner with ASIC micro-architecture, design, and verification teams to take features from specification to silicon.
  • Engage with switch customers and XPU partners on product deployment, solutions, guidance, and field debugging.
  • Align architecture with software SDKs, product roadmaps, and customer-facing messaging.

Requirements

  • Bachelor’s degree in Electrical Engineering, Computer Science, or a related field, with 12+ years of relevant industry experience.
  • Working knowledge of ASIC micro-architecture, including complexity and PPA trade-offs involving power, performance, and area.
  • Traffic management expertise covering scheduling disciplines and buffer management.
  • Strong interpersonal, communication, problem-solving, and attention-to-detail skills.
  • Ability to work independently and drive work forward.
  • Fluent use of AI in the workflow.

Nice to have

  • Networking experience with Ethernet switching and data center network design, including L2/L3 forwarding, tunneling and overlays, load balancing, telemetry, congestion control, and lossless transport.
  • Knowledge of AI network fabrics and workloads for training and inference, including scale-up and scale-out fabrics, disaggregation, MoE models, collective communication, RoCEv2, congestion control, and load balancing.
  • Familiarity with emerging AI fabric standards such as Ultra Ethernet.
  • Architecture modeling in C++, SystemC, or a comparable language; proficiency in Python or another scripting language.
  • Verilog or SystemVerilog experience and familiarity with RTL design, physical design, and digital verification flows.

Culture & Benefits

  • Full-time position based onsite in San Jose, California.
  • Eligible for a discretionary annual bonus and new-hire and annual equity awards.
  • Medical, dental, and vision plans, 401(k) participation with company matching, and an Employee Stock Purchase Program.
  • Employee Assistance Program, paid holidays, paid sick leave, vacation time, and applicable paid family and other leaves.
  • Applicants outside the USA should provide a home address for future correspondence.

Hiring process

  • First-time users must create a candidate login account before applying; existing users must sign in to their candidate account.

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 →