AI Observability & Governance Engineer - Agentic ERP Platform

Benefits

Additional Information

About Rimini Street, Inc. Rimini Street, Inc. (Nasdaq: RMNI), a Russell 2000® Company, is a proven, trusted global provider of end-to-end, mission-critical enterprise software support, managed services and innovative Agentic AI ERP solutions, and is the leading third-party support provider for Oracle, SAP and VMware software. Our comprehensive portfolio of unified solutions help run, manage, support, customize, configure, connect, protect, monitor, and optimize enterprise application, database and technology software, enabling our clients to achieve better business outcomes, significantly reduce costs and reallocate resources towards strategic projects. The Company has signed thousands of contracts with Fortune Global 100, Fortune 500, midmarket, public sector and government organizations who selected Rimini Street as their trusted, proven mission-critical enterprise software solutions provider and achieved better operational outcomes, realized billions of US dollars in savings and funded AI and other innovation investments. We are actively seeking an Observability & Governance Engineer - Agentic ERP Platform. This hybrid role is based in our Selangor or Penang office. Position Summary The Observability & Governance Engineer owns the consumer side of Rimini Street's Agentic ERP Platform observability and audit infrastructure - the dashboards, alerts, compliance evidence chain, audit query tooling, and customer-facing reporting that turn platform telemetry into something auditors, customer security teams, and operations leaders can actually use. This role makes the platform's emitted signals visible, queryable, and defensible. Reporting to the Security & Identity Lead, this engineer partners closely with the security control plane - producing the audit evidence and compliance posture that prove platform controls are working, and operating the LLM and operational observability that surfaces issues to support, security, and customer-facing teams. The role sits at the boundary between platform telemetry and the people who depend on it - auditors who need SOX-grade evidence, customer security teams who need posture reporting, support teams who need actionable alerts, and the Indemnification Control Owner who needs integrated compliance status. The ideal candidate combines hands-on observability engineering with a structured approach to compliance evidence and a track record of building dashboards that are actually used. Essential Duties & Responsibilities Compliance Evidence & Audit Chain Operate the dual-stream audit logging architecture (operational telemetry plus immutable compliance records) and ensure every agent action produces a complete, queryable audit chain. Build audit query tooling that lets internal teams and customer auditors trace any agent action back through its decision chain: session, tool invocation, authorisation decision, policy version, before/after state. Produce SOX-grade compliance evidence packages on demand for client audits and regulatory reviews - supporting the Security & Identity Lead's accountability for platform compliance posture. Implement and maintain audit log retention, immutability guarantees, and access controls aligned to client and regulatory requirements. Support the Indemnification Control Owner with quarterly integrated configuration audit reports covering all monitored vendor indemnification conditions. Dashboards & Customer-Facing Reporting Build and maintain operational dashboards covering platform health, agent activity, policy decisions, model usage, cost, and quality signals. Design and deliver customer-facing posture reports: platform health, security status, audit completeness, and SLA compliance. Build alert routing and escalation policies that turn signal noise into actionable operational events for support and engineering teams. Maintain release advisory generation and posture reporting workflows for client distribution. LLM Observability Operations Operate the LLM observability layer (LangFuse self-hosted) and ensure complete capture of prompts, responses, costs, and quality signals. Build dashboards for token usage, model cost, latency distributions, and quality drift across the model gateway. Implement cost governance reporting: per-customer cost tracking, budget alerts, and cost optimisation insights for the AI/ML Lead. Coordinate with the AI/ML Lead on model quality and evaluation signal integration into operational dashboards. Signal Consumer Integration Operate as the primary consumer for signals produced by Platform Runtime and Platform Experience engineering - audit records, OPA policy decisions, OpenTelemetry traces, LangFuse LLM traces, model gateway cost events, agent activity signals. Build the compliance chain integration that aggregates these signals into the artefacts compliance and audit teams require. Maintain runtime security operations: vulnerability monitoring triage, air-gap update distribution, client patch compliance tra

Your Match

How well this role fits your profile.

Company Intel

What employees say

Worked at riministreet? Share your experience