- Classify and correlate failures
- Collect and interpret metrics and telemetry for Discovery health
- Convert runbooks into reusable agentic workflows
- Design and build AI agents for Discovery log analysis at scale
- Develop agentic observability for MID Servers and Discovery schedules
- Implement testing guardrails and human approval for production changes
- Integrate LLM APIs with RAG for troubleshooting workflows
- Perform root cause analysis
- Recommend or generate corrective actions
Perks/Benefits:
- Annual learning budget
- Flexible hours
- Learning budget
- Mentorship
- Remote work
- Supportive culture
- Well-being programs