Назад
Company hidden
7 дней назад

Senior Software Engineer, Machine Learning Platform - Serving (US) (ML)

167 800 - 246 800$
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
Senior Software Engineer, Machine Learning Platform - Serving (US) (ML): Building self-serve machine learning serving infrastructure that connects request routing and online feature retrieval with CPU and GPU model inference at tens of millions of predictions per second with an accent on latency, reliability, resource efficiency, and scale. Focus on designing disaggregated serving components, Kubernetes deployment and autoscaling, integrating open-source inference technologies, and improving production performance and reliability.

Location: San Francisco, CA; Sunnyvale, CA; or Seattle, WA, United States

Base salary: $167,800–$246,800 USD annually, localized by work location.

Company

hirify.global is a technology and logistics company building services that support local commerce, delivery, and related goods.

What you will do

  • Build self-serve tools, APIs, and workflows for deploying, configuring, validating, and operating machine learning models.
  • Connect request routing and online feature retrieval with CPU and GPU model inference on a platform serving tens of millions of predictions per second.
  • Evaluate and integrate open-source inference frameworks and models into reliable production services.
  • Develop modular, disaggregated serving components that scale independently.
  • Improve Kubernetes deployment, resource management, autoscaling, latency, availability, and cost efficiency.
  • Own projects from technical design through testing, rollout, production support, benchmarking, profiling, on-call, and operational improvements.

Requirements

  • 2+ years of software engineering experience building and maintaining production services or infrastructure.
  • Strong computer science fundamentals and proficiency in a backend or systems programming language such as Java, Kotlin, Go, C++, or Python.
  • Understanding of distributed systems fundamentals, including concurrency, networking, timeouts, failure handling, and performance trade-offs.
  • Ability to independently turn a defined problem into a technical design, tested implementation, and safe production rollout.
  • Experience debugging production systems and using operational data to improve reliability, performance, or cost.
  • Ability to collaborate with internal customers and partners to make complex infrastructure easier to adopt.
  • Degree in Computer Science or a related field, or equivalent practical experience.

Nice to have

  • Experience with ML inference infrastructure, online feature retrieval, or latency-sensitive distributed services.
  • Experience operating containerized workloads on Kubernetes, including deployment, resource management, or autoscaling.
  • Experience building self-serve developer platforms, APIs, or automation for engineers.
  • Experience integrating open-source infrastructure or models and validating production behavior.
  • Familiarity with CPU/GPU performance profiling, inference runtimes, or model deployment workflows.

Culture & Benefits

  • Comprehensive benefits for regular employees, including medical, dental, vision, disability, life insurance, and mental health support.
  • 401(k) with employer matching, paid parental leave, wellness benefits, commuter benefits match, paid time off, and paid sick leave.
  • Flexible paid time off and 80 hours of paid sick time annually for salaried roles.
  • Additional compensation may include equity grants.
  • Participation in on-call support and production operations is part of the role.

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 →