• Build and operationalize models for anomaly detection, forecasting, early incident warning, performance regression detection, saturation/capacity risk, and service health scoring. • Correlate logs/metrics/traces/events with topology, deployment, change, and business signals to identify drivers of degradation and reduce time-to-diagnosis. • Prototype and advance agentic workflows that assist with triage, signal enrichment, event clustering, summarization, and guided next-best-action recommendations. • Use and extend enterprise observability platforms (Splunk, Datadog, Cribl, SolarWinds, Langfuse) to extract signals, engineer features, validate hypotheses, and operationalize outcomes. • Define data quality checks, feature pipelines, and scalable methods for working with high-volume telemetry (batch and/or streaming), partnering with platform teams as needed. • Establish model performance measures aligned to operational goals (noise reduction, precision/recall of detections, lead time to failure, MTTR improvements); monitor drift and iterate. • Communicate findings to technical and non-technical stakeholders with clear recommendations, tradeoffs, and measurable results. • Ensure solutions align with Leidos standards for security, privacy, governance, and responsible AI practices.