• Own the end-to-end observability strategy for Ava, defining the standards, tools, and patterns that ensure reliable visibility across infrastructure and agentic components. • Design and implement correlation models that link agent behavior, LLM interactions, and SaaS telemetry into cohesive, actionable insights. • Unify observability tooling across teams, ensuring metrics, logs, and traces flow into a central platform (e.g., Observe, Datadog, or equivalent). • Collaborate with engineering and QA to embed observability best practices into development workflows, CI/CD, and quality gates. • Establish enablement frameworks—documentation, dashboards, and templates—that make observability self-serve for all engineering teams. • Partner with teammates to ensure observability aligns with infrastructure reliability, alerting, and incident response patterns. • Contribute to performance and reliability strategy, helping define how we measure agent quality, responsiveness, and system scalability.