The deployment of
CyberAgent AI
AdTech SRE👌

apiVersion: teams.sre/v1
kind: SRETeam
metadata:
  name: adtech-sre
  labels:
    team: adtech-sre
    department: engineering
spec:
  teamSize: 6
  responsibilities:
    - automation: "Automate toil and repetitive tasks to focus on high-value activities."
    - incidentManagement: "Lead incident response to maintain service SLAs."
    - postMortemCulture: "Facilitate blameless postmortems and continuous learning."
    - capacityPlanning: "Forecast and manage system capacity and performance."
    - disasterRecovery: "Develop and execute disaster recovery plans."
    - toolingDevelopment: "Create and maintain internal tools for deployment, monitoring, and operations."
    - performanceMonitoring: "Monitor system performance and create benchmarks for improvements."
    - documentation: "Document systems architecture and operational procedures."
  skillsRequired:
    - languages: ["Go", "Python", "Shell", "Japanese"]
    - technologies: ["Kubernetes", "Docker", "Terraform", "Prometheus", "Datadog"]
    - systemsKnowledge: ["Linux", "Networking", "Cloud Services"]
    - softSkills: ["Problem-solving", "Communication", "Teamwork", "🍻"]
  traits:
    - proactive
    - detailOriented
    - collaborative
    - adaptable
    - patient
    - friendly
  performanceMetrics:
    - SLI: "Service Level Indicators"
    - SLO: "Service Level Objectives"
    - MTTR: "Mean Time To Recover"
    - MTBF: "Mean Time Between Failures"
    - ChangeFailureRate: "< 0.5%"