Senior Software Engineer, Triage Services

What you'll do

• Architect and deliver the agentic triage platform, including orchestration, integrations, data pipelines, and production lifecycle.
• Define agent evaluation and observability practices, and use results to improve reliability and automation quality.
• Drive adoption across Core OS, Hardware, and Silicon teams; mentor engineers and oversee production operations.

What they ask for

• 6+ years building and operating production distributed systems or data platforms at scale.
• Expert-level Python, strong system design, and architecture ownership for services used by other teams.
• 2+ years shipping LLM-based or agentic systems to production, including tool calling, orchestration, and guardrails.
• Experience designing ML/LLM evaluation frameworks; deep working knowledge of RAG, embedding generation, vector databases, and agentic-workflow data preparation.

Nice to have

• MS or PhD in Computer Science, Machine Learning, or a related field.
• Kernel or OS-level debugging, crash analysis, large-scale telemetry, or widely adopted engineering platforms.

Pay

$150,400 and $277,600 (base salary)

Tools

Python, LLM, RAG, vector databases

AI focus

Build and lead production agentic systems for autonomous software-crash triage, including orchestration, tool integration, evaluation, guardrails, and feedback loops.