Senior Site Reliability Engineer (SRE & AI Platform Operations)
Core
Take full technical ownership of production reliability, distributed observability, deployment safety, cost optimization, and AI runtime infrastructure across high-velocity microservices and cloud workloads.
Role type
Senior Site Reliability Engineer (SRE & AI Platform Operations)
Builds
High-velocity microservices, AI runtime infrastructure, and automated diagnostic tooling on Google Cloud.
Domain
Cloud Infrastructure & AI Platform Operations
Deliverable
production ML models
Required skills
SLO/SLI management, distributed tracing, CI/CD pipeline automation, FinOps, incident management, capacity planning, Infrastructure as Code (Terraform), Python, TypeScript, PHP (Laravel), Linux troubleshooting, container orchestration.
Preferred skills
AI operations (LLM integrations, vector workflows), semantic pipelines, background task orchestration.
Technologies
Google Cloud Platform, Google Cloud Run, Terraform, Sentry, Redis, Laravel, Astro, GitHub Actions.
Responsibilities
Define and enforce SLOs/SLIs across core customer journeys; expand distributed observability and telemetry; evolve CI/CD pipelines with canary traffic shifting and automated rollbacks; architect and scale AI runtime infrastructure; optimize cloud and AI runtime costs; lead incident response and post-mortems; drive capacity forecasting and disaster recovery validations; own declarative infrastructure workflows with strict security; build internal tooling to eliminate toil.
Seniority
Senior, hands-on IC