Building and maintaining dashboards, alerts, and monitoring for inference workloads using Akamai's existing observability platform
Writing automation and tooling in Python or Go to reduce operational toil and improve system reliability
Participating in on-call rotations, responding to production incidents, and contributing to post-mortem analysis
Building and improving runbooks for inference-specific operational procedures, integrating into Akamai's existing incident management processes
Contributing to SLO tracking and reporting, identifying trends and areas for improvement
Supporting CI/CD pipeline maintenance, deployment safety checks, and rollback procedures
Collaborating with product engineering teams to troubleshoot complex problems across the stack

Have commercial experience in Site Reliability Engineering
Show proficiency in a programming language such as Python or Go, with experience creating automation solutions.
Have experience with Linux systems administration and the ability to troubleshoot complex infrastructure issues
Show familiarity with Kubernetes and containerization concepts
Have experience with monitoring and observability tools such as Prometheus, Grafana, or similar
Have exposure to CI/CD pipelines and infrastructure-as-code tools (Terraform, SaltStack, or equivalent)
Show a willingness to learn and grow, with genuine curiosity about AI infrastructure and distributed systems

Site Reliability Engineer II

Key skills