Staff SRE for AI Workloads and Observability

Take on a critical role as a Staff Site Reliability Engineer focused on optimizing AI workloads. This position empowers you to define engineering standards and improve our reliability practices.
You will drive the organization toward a proactive reliability approach as you partner with existing engineers. Your efforts will not only enhance incident response strategies but also establish effective tools that improve system observability and response metrics, allowing for sustainable improvements.
Key Responsibilities:
• Set SLIs and SLOs based on critical user interactions
• Direct production incident responses and lead effective postmortems
• Develop meaningful dashboards that enhance system understanding
• Mentor the engineering team for technical skill enhancement
• Lead architectural improvements for reliability tools
Requirements:
• Profound experience with Site Reliability Engineering and AWS
• Background in handling production incidents effectively