Staff Site Reliability Engineer (AI Platform)

📋 Description

• Own reliability and performance of AI infrastructure: gateway and inference.
• Design/evolve AI Gateway: routing, failover, rate limiting, caching.
• Build observability for AI systems: latency, throughput, SLOs, metrics.
• Drive cost optimization and FinOps for AI workloads.
• Run capacity planning and incident response; write runbooks.
• Scale AI expertise across the org; set standards and coach teams.

🎯 Requirements

• 5+ years in SRE/platform/infrastructure with production ownership.
• Hands-on with LLM-backed systems in production (Bedrock, OpenAI, Anthropic).
• Cloud-native: AWS, Kubernetes, Terraform/IaC, CI/CD.
• Observability: Prometheus/Grafana, OpenTelemetry, define SLOs.
• Proven cost-optimization: cut cloud/inference spend and visibility.
• Staff-level influence: set technical direction beyond your team.

🎁 Benefits

• Hybrid onboarding to start remote work; relocation support.
• Comprehensive health insurance for you and family.
• Professional development budget for conferences and courses.
• Flexible benefits budget; you pick perks for health, home office, etc.
• Hybrid work and flexible time off, planned with your team.
• In-office perks: free meals and snacks.