Good to have experience integrating AI/LLM capabilities into applications for incident analysis, contextual recommendations, and operational decision support.
Experience implementing alert correlation, deduplication, enrichment, and prioritization to reduce noise and improve incident detection.
Strong experience developing automated remediation workflows with approval controls, execution validation, audit trails, and recovery safeguards.
Experience integrating monitoring platforms with incident management systems, knowledge repositories, and notification or escalation services.
Strong understanding of distributed systems, Linux, networking, databases, and application performance, with the ability to translate failure patterns into platform capabilities.
Ability to evaluate platform reliability and AI output quality, measure operational outcomes, and improve capabilities using engineer feedback.
Excellent communication and collaboration skills, with the ability to work with monitoring teams, service owners, and engineers to onboard services and define requirements.
Good-to-Have
Experience with agentic AI frameworks, tool calling, retrieval-augmented generation, and vector databases.
Knowledge of anomaly detection, time-series analysis, and predictive techniques for identifying recurring alarm patterns.
Experience building centralized notification services, automated escalation calls, and incident communication workflows.
Familiarity with OCI, Kubernetes, and Infrastructure-as-Code tools such as Terraform or Ansible.
Experience with observability platforms such as OCI Observability, Prometheus, Grafana or equivalent tools.
Experience using AI coding assistants to improve operational scripts and validate proposed changes.
Knowledge of SLOs, error budgets, and incident metrics such as detection time, recovery time, and recurrence rate.