About the role
Provide on-call coverage for incoming incidents across CDI services (Power BI, Fabric, Power Query Online, Gateway, connectors) — initial investigation, severity assessment, and routing to owning engineering teams. Build and extend AI-driven agents that triage incoming ICM alerts: correlate with recent deployments and feature flag rollouts, match against known issues and TSGs across Fabric and Power Platform and produce initial assessments with suggested severity and owning team. Build incident lifecycle automation — incident summarization, customer communications drafts, postmortem generation, and reporting — so that human judgment is reserved for high-severity work rather than routine authoring. Configure and extend ICM routing rules and intelligent classification systems based on service tree, alert signatures, and historical patterns; raise the quality bar on incoming CSS escalations. Measure and improve first-time mitigation (FTM), incident deflection rates, and time-to-triage; use the data to identify patterns, propose new TSGs, and drive systemic improvements. Partner across the CDI organization and broaden scope into adjacent engineering products and services as automation matures and operational load decreases. Bachelor's Degree in Computer Science or related technical field AND 2+ years technical engineering experience with coding in languages including, but not limited to, C, C++, C#, Java, JavaScript, or Python OR equivalent experience. Experience building AI/ML-driven automation, agents, or intelligent workflows (e.g., using LLMs, Copilot extensibility, MCP servers, or agentic frameworks). Familiarity with Live site ecosystem management: log traversal, incident management, telemetry analysis, and related diagnostic workflows. Experience with Azure, Power BI, and Fabric services. Experience with Troubleshooting Guide (TSG) authoring and incident pattern analysis. Understanding of SLA management, customer communications, and escalation workflows for cloud services. Comfort partnering across geographically distributed teams and contributing to an on-call rotation with multi-timezone coverage.
