Senior II Site Reliability Engineer

Akamai•Cambridge, MA

4d•$146,400 - $263,600•Hybrid

About The Position

This role is for a Senior II Site Reliability Engineer on the Akamai Inference Cloud Team, which is part of Akamai's Cloud Technology Group. The team designs, implements, deploys, and operates AI platforms for customer inference models and developer AI applications. In this position, you will lead reliability workstreams for Akamai's serverless inference platform, design SRE tooling and automation, and drive technical decisions. There are opportunities to mentor other SREs, influence architecture decisions with product engineering teams, and shape SRE practices for AI inference workloads and GPU infrastructure at scale.

Requirements

8+ years of experience in SRE, infrastructure engineering, or platform engineering, working with large-scale distributed systems
Proven track record of defining SLO/SLI frameworks, building observability platforms, and running incident management processes at scale
Extensive Kubernetes and containerization experience at scale, including autoscaling, resource scheduling, and container orchestration for compute-intensive workloads
Experience building automation and tooling in Python or Go, with familiarity in CI/CD pipelines, deployment safety, and infrastructure-as-code
Ability to lead technical initiatives across teams, mentor other engineers, and drive complex reliability problems to resolution independently
Experience with or exposure to AI/ML infrastructure, model serving, or GPU workloads

Responsibilities

Taking ownership of observability strategy for the serverless inference platform, designing telemetry, dashboards, and alerts, defining SLO/SLI frameworks, and driving improvements when targets are missed
Building production-grade automation and tooling that reduces operational toil, improves incident response, and sets patterns that other SREs adopt
Owning incident management integration for inference workloads, designing frameworks, leading incident response during on-call rotations, and driving systemic improvements from post-mortems
Defining and implementing deployment safety practices including progressive rollouts, canary analysis, and rollback automation, establishing standards for the team
Partnering with product engineering teams to influence architecture decisions, ensure operational readiness, and represent the SRE perspective in design reviews
Mentoring Senior and mid-level SREs through code reviews, design discussions, and hands-on problem-solving