← Zurück zur Liste
Stelle · Senior

Senior Site Reliability Engineer

DevOps / SRE • Senior • Remote • Vollzeit • Polen Polen

On the Akamai Inference Cloud team you will own reliability workstreams for the serverless inference platform, build automation and tooling, and contribute to architecture decisions.

Responsibilities

  • ▹Build and maintain observability for AI workloads: telemetry, dashboards, alerts, SLO/SLI tracking, and drive improvements when targets are missed
  • ▹Write automation and tooling to reduce operational toil, improve deployment safety and accelerate incident response
  • ▹Integrate AI workloads into Akamai's incident management processes, build runbooks, join on-call rotations and run blameless post-mortems
  • ▹Build and maintain CI/CD integrations, deployment safety checks and rollback automation
  • ▹Collaborate with product engineering teams on reliability, architecture and operational readiness for releases
  • ▹Contribute to capacity planning, autoscaling configuration and workload scheduling for AI compute infrastructure

Requirements

  • ▹Expertise in SRE, infrastructure or platform engineering, managing large-scale distributed systems
  • ▹Expertise in Kubernetes and large-scale containerization systems
  • ▹Defining SLOs and working with observability tools such as Prometheus, Grafana and distributed tracing
  • ▹Proficiency in Python or Go for automation, CI/CD, deployment safety and infrastructure-as-code such as Terraform
  • ▹Interest in or experience with AI/ML infrastructure, model serving or GPU workloads
  • ▹Resolve issues independently while maintaining accountability
  • ▹Accountability for reliability and effective collaboration with an engineering team unfamiliar with SRE practices

Soft skills

IndependenceAccountabilityCollaboration

What we offer

  • ▹FlexBase flexible working program: work from home, the office or both (in the country advertised)
  • ▹Benefit options covering health, finances, family and time at work

About the company

Akamai runs the world's most distributed compute platform from cloud to edge, powering and protecting life online. The Inference Cloud team designs and operates AI platforms on which customers run inference models.

Ähnliche Stellen