Назад
обновлено 1 месяц назад

Senior Site Reliability Engineer (AI/ML Inference)

Формат работы
remote (Global)
Тип работы
fulltime
Грейд
senior
Английский
b2
Страна
UK/CR/Netherlands +2 еще
Вакансия из списка Hirify.GlobalВакансия из Hirify RU Global, списка компаний с восточно-европейскими корнями
Для мэтча и отклика нужен Plus

Мэтч & Сопровод

Для мэтча с этой вакансией нужен Plus

Описание вакансии

Текст:
/
TL;DR
Senior Site Reliability Engineer (AI/ML Inference): Owning the reliability, performance, and observability of a massive-scale AI inference platform with an accent on designing telemetry, optimizing Kubernetes autoscalers, and hardening distributed back-end systems. Focus on building self-healing systems, debugging performance from kernel to application layer, and ensuring flawless behavior under extreme load.

Location: Amsterdam, Berlin, London, Prague, or remote within Europe

Company

Nebius builds a full-stack AI cloud platform for data processing, model training, and production deployment, including large-scale GPU infrastructure and inference services.

What you will do

  • Own the reliability, performance, and observability of the Token Factory inference platform.
  • Design and refine telemetry pipelines for metrics, logs, and traces at very large scale.
  • Tune Kubernetes autoscalers and GPU workloads to improve efficiency and reliability.
  • Create Terraform modules and infrastructure-as-code patterns for resilient clusters.
  • Harden request routing and retry logic, and automate incident detection, isolation, and remediation.
  • Lead post-mortem improvements and collaborate with software engineers to make reliability a platform feature.

Requirements

  • Deep experience with Kubernetes, Prometheus, Grafana, Terraform, and infrastructure-as-code.
  • Comfortable scripting in Python or Bash.
  • Strong understanding of alert design, SLOs, and high-throughput APIs.
  • Production experience with distributed back-end systems and troubleshooting failures.
  • Experience with GPU-heavy workloads, such as vLLM, Triton, Ray, or another accelerator stack.
  • Applicants must be authorized to work in the country in which they apply and provide proof of employment eligibility.

Nice to have

  • Background in MLOps or model-hosting platforms.
  • Experience with multimodal AI infrastructure.

Culture & Benefits

  • Competitive compensation.
  • Career growth and learning opportunities.
  • Flexibility and ownership.
  • Collaborative, innovative, and international environment.
  • Opportunity to work on impactful AI projects with experienced engineering teams.

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 →