Setting the technical direction for AI-powered alert triage, the fully remote Staff Software Engineer, AI will facilitate architecture decisions, design incident grouping, and mentor engineers while ensuring the system's workflow durability and effectiveness in reducing mean time to triage. Key Responsibilities: Facilitate architecture decisions for alert correlation and LLM reasoning across the investigation pipeline Own the design for incident grouping, confidence scoring, and narrative presentation to analysts Define durable workflow architecture and contribute hands-on to resolve triage and workflow issues across teams Required Qualifications: Authority in Go and Python with a proven track record in building reliable production systems Hands-on expertise in LLM tool calling and applying LLM reasoning to real-world problems Mastery of Temporal workflow design, including determinism and versioning Experience building novel solutions combining graph-based reasoning with LLM-driven decision-making Deep understanding of telemetry and protocols for constructing usable network and system topologies