SRE II: AI Inference Cloud Reliability & Automation
Posted Updated
Description
Akamai is seeking a Senior Site Reliability Engineer for our Inference Cloud Team in Kraków, Poland. You will own reliability workstreams for the serverless inference platform and build automation to accelerate incident response.
Join a team focused on GPU workloads, Kubernetes at scale, and architecture decisions to ensure confident product releases and robust operational readiness. On-call rotates and blameless post-mortems are part of the cycle.
Own reliability workstreams for Akamai's serverless inference platform. Build automation and tooling to reduce operational toil and improve deployment safety. Contribute to architecture decisions and ensure operational readiness for releases. Develop expertise in GPU infrastructure and AI inference workloads. Participate in on-call rotations and post-mortems to drive blameless learning. Extensive experience with large-scale distributed systems. Expertise in Kubernetes and containerization. Proficiency in Python or Go for automation. Experience with observability tools and incident management is a plus. Experience with AI/ML infrastructure or GPU workloads is beneficial.Skills
Sign in to read and join the discussion.