Software Engineer, Triage Services
Core
Design and build AI-powered agentic systems to detect, analyze, and classify low-level software crashes across Apple platforms, serving as the first line of defense for Core OS technologies.
Role type
Senior IC distributed systems engineer specializing in AI agent development
Builds
Production-grade infrastructure for AI/ML workloads and autonomous triage services
Domain
Operating Systems (Core OS) + Applied AI/LLMs
Deliverable
production ML models
Required skills
Python, distributed systems, LLM and agent development, RAG architectures, vector databases, eval frameworks for agent quality
Preferred skills
OS-level debugging, crash analysis, large-scale telemetry systems, mentorship
Technologies
Python, LLMs, RAG, vector databases, eval frameworks
Responsibilities
Design and maintain AI agent workflows for automated triage and root-cause analysis; Evaluate and improve agent reliability including prompt design and guardrails; Instrument agent pipelines to surface failures and drift; Collaborate with Core OS teams to refine agent behavior; Own the full lifecycle of production agents including on-call ownership and mentorship.