AI Observability & Governance Engineer – Agentic ERP Platform

About the role

Rimini Street, a global provider of enterprise software support and Agentic AI ERP solutions, is hiring an Observability & Governance Engineer for its Agentic ERP Platform. This hybrid role is based in the Selangor or Penang office and reports to the Security & Identity Lead. It owns the consumer side of the platform's observability and audit infrastructure: dashboards, alerts, compliance evidence chains, audit query tooling and customer-facing reporting that turn platform telemetry into usable information for auditors, security teams and operations leaders.

Key responsibilities

• Run the dual-stream audit logging architecture so every agent action has a complete, queryable audit chain, including session, tool invocation, authorisation decision, policy version and before/after state.
• Produce SOX-grade compliance evidence packages on demand for client audits and regulatory reviews, and support the Indemnification Control Owner with quarterly configuration audit reports.
• Maintain audit log retention, immutability guarantees and access controls, and partner with the Observability Specialist on telemetry pipeline reliability.
• Build operational dashboards and customer-facing posture reports covering platform health, security status, audit completeness and SLA compliance.
• Build alert routing and escalation policies, and maintain release advisory generation and posture reporting workflows.
• Operate the self-hosted LangFuse LLM observability layer, build dashboards for token usage, model cost, latency and quality drift, and implement cost governance reporting for the AI/ML Lead.
• Integrate signals such as OpenTelemetry traces, OPA policy decisions and agent activity into the compliance chain, and run runtime security operations including vulnerability monitoring triage and air-gap update distribution.
• Partner with the Platform Runtime Engineer, AI/ML Lead, QA Testing Lead and US Delivery on audit integration, model evaluation signals, log validation and customer audit responses.

Required profile

• 6+ years of observability, SRE or platform operations experience, with at least 2 years owning customer-facing or audit-facing reporting.
• Hands-on experience with distributed tracing, metrics, log aggregation and dashboards at production scale.
• Proven experience producing compliance evidence for SOC 2, ISO 27001, SOX or equivalent frameworks.
• Experience with multi-tenant SaaS or enterprise platforms where customer-facing reporting is a product requirement; enterprise software, regulated industries or B2B background preferred.

Required skills

• Observability stack: OpenTelemetry, Jaeger, Prometheus, Grafana, OpenSearch.
• PostgreSQL and SQL for audit storage and queries; Python and/or Go for tooling.
• Grafana dashboard design, alert rules and dashboard-as-code workflows.
• Kubernetes operations, service mesh telemetry and container logging.
• Preferred: LangFuse, OPA, Restate, SIEM familiarity, FinOps tools, AI assurance frameworks and vulnerability management tooling.