- Build agentic observability for MID Servers and Discovery schedules
- Classify and correlate failures
- Collect aggregate and interpret service telemetry and metrics
- Convert runbooks into reusable agentic workflows
- Design and build AI agents for log analysis at scale
- Implement testing and guardrails with human approval
- Integrate LLM APIs using RAG
- Perform root cause analysis
- Recommend or generate corrective actions
- Use vector databases for retrieval
Perks/Benefits:
- Flexible hours
- Learning budget
- Mentorship
- Remote work
- Support programs
- Well-being programs