Description
The role leads the architecture and delivery of an AI-powered, agentic triage platform for detecting, analyzing, and classifying low-level software crashes across Apple platforms. Responsibilities include agent orchestration, tool integration, data pipelines, production infrastructure, evaluation and observability, cross-team adoption, operational excellence, and mentoring engineers. The position requires extensive distributed-systems and Python experience, production LLM or agentic-systems work, ML evaluation expertise, RAG and vector-database knowledge, and technical leadership.
