Senior Site Reliability Engineer

Quick Facts

• Role: Senior Site Reliability Engineer

• Focus: Reliability for a serverless AI inference platform (observability, automation, incident response, and operational readiness)

Description

Own reliability workstreams for a serverless AI inference platform, building observability, automation, and tooling to improve deployments, incident response, and overall reliability. Work with product engineering teams on architecture and operational readiness, including CI/CD integration, deployment safety checks, and rollback automation. Build expertise in GPU infrastructure, large-scale Kubernetes, and AI inference workloads.

Responsibilities

• Build and maintain observability for AI workloads (telemetry, dashboards, alerts, SLO/SLI tracking) and improve performance when targets are missed

• Write automation and tooling to reduce operational toil, improve deployment safety, and accelerate incident response

• Integrate AI workloads into incident management processes (runbooks, blameless post-mortems, on-call participation)

• Maintain CI/CD integrations, deployment safety checks, and rollback automation

• Collaborate with product engineering to improve reliability, contribute to architecture decisions, and ensure operational readiness

• Contribute to capacity planning, autoscaling configuration, and workload scheduling for AI compute infrastructure

Benefits

• Opportunities to learn, grow, and take on new roles with development programs and mentoring

• Career support through internal events and learning tools