- Analyze discovery ecosystem health using metrics and telemetry
- Classify and correlate failures
- Convert runbooks into reusable agent workflows
- Design and build AI agents for continuous log analysis
- Develop agentic observability for MID Servers and Discovery schedules
- Implement guardrails and human approval workflows
- Integrate LLM APIs with retrieval augmented generation
- Perform root cause analysis
- Recommend and generate corrective actions
Perks/Benefits:
- Annual learning budget
- Flexible hours
- Mentorship
- Remote work
- Support programs
- Well-being programs