Site Reliability Engineer II
Core
Build and maintain observability, automation, and reliability for Akamai's serverless AI inference platform.
Role type
Site Reliability Engineer II (AI Infrastructure)
Builds
Serverless inference platform for AI workloads
Domain
Cloud computing / AI Infrastructure
Deliverable
production ML models
Required skills
Linux systems administration, Python or Go, Kubernetes, Prometheus, Grafana, CI/CD pipelines, Infrastructure-as-Code (Terraform, SaltStack)
Preferred skills
GPU infrastructure, SLO tracking, incident management processes
Technologies
Python, Go, Kubernetes, Prometheus, Grafana, Terraform, SaltStack
Responsibilities
Build and maintain dashboards, alerts, and monitoring for inference workloads; Write automation and tooling to reduce operational toil; Build and improve runbooks for inference-specific operational procedures; Contribute to SLO tracking and reporting; Support CI/CD pipeline maintenance, deployment safety checks, and rollback procedures; Participate in on-call rotations, respond to production incidents, and conduct blameless post-mortems
Seniority
Mid-level, hands-on IC