Agentic AI Engineer

riministreet; Hyderabad; On-site; INR 1,500,000 - 2,100,000; Full time

Job summary

Rimini Street, Inc. in India seeks an Agentic AI Engineer to design and build the cognitive architecture of AI agents that interact with enterprise ERP systems. This role focuses on multi-agent coordination, dynamic tool use, and governance within autonomous workflows.

The position sits in India and involves shaping the emerging field of agentic systems design, with collaboration across ERP domains and enterprise tech teams.

Qualifications

• Design cognitive architecture for AI agents interacting with ERP systems.
• Develop multi-agent coordination patterns for enterprise workflows.
• Define governance and escalation within risk-tiered autonomy frameworks.

Responsibilities

• Design agent cognitive architecture for ERP tasks with governance checkpoints.
• Build agent personas for Rimini Solution domains (Finance, Procurement, etc.).
• Architect dynamic tool selection strategies for MCP tools.
• Design conversation state management for long-running agent sessions.
• Build confidence scoring frameworks translating uncertainty into governance decisions.

Skills

Cognitive architecture

Multi-agent coordination

Tool selection strategies

LLM integration

Tools

MCP tools

Job description

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 a Agentic AI Engineer . This role is based in India.

About Rimini Street, India, GCC.

Rimini Street Inc, HQ : Las Vegas, NV, USA a disruptor in third party ERP support services, established undisputed leadership and as a natural progression, entered India with Rimini Street, India GCC India kick starting operations in Hyderabad , in 2013 with Global Client Onboarding Services, IT shared services and Global Service Development. In no time, Rimini Street, India GCC started Bengaluru operations going up the value chain with more complex product development (Oracle, SAP, Peoplesoft, JDE etc.) & advanced services (Managed services, Professional services, Security Managed Services etc).

Rimini Street, India GCC gained valuable share in bringing the reputation to Rimini Street Inc of being a global provider of unified support and managed service solutions for enterprise software. Today, Rimini Street, India GCC is a family of about 800+ full time talented individuals, thanks to the remarkable talent that has supported the expansion.

Rimini Street, India has nicely emerged as Global Capability Centre (GCC), and proudly says, "if you are best of the best, you belong to Rimini". We are on a mission to contribute significantly to our "Rimini ONE" program, a turnkey Rimini Street service program that offers a comprehensive set of unified, integrated services that can run, manage, support, customize, configure, connect, protect, monitor, and optimize your Oracle and SAP ERP, database, and technology software.

Role Overview

The Agentic AI Engineer is responsible for designing and building the cognitive architecture of AI agents that interact with enterprise ERP systems. This is not prompt engineering - it is the design of agent behavior systems: how agents reason through ambiguous multi-step problems, when and how they use tools, how they coordinate with other agents, how they govern themselves within risk-tiered autonomy frameworks, and how they escape to humans at the right moments.

This role sits at the intersection of AI engineering and enterprise systems architecture. Where the GenAI Engineer (junior/mid-level) focuses on individual prompt design, context window management, and LLM API integration, the Agentic AI Engineer designs the higher-order systems: multi-agent coordination patterns, cognitive reasoning chains for complex ERP workflows, dynamic tool selection strategies, autonomous vs. supervised decision boundaries, and the feedback loops that make agents learn from their operational experience.

This is an emerging discipline. The industry is evolving from simple prompt engineering toward what might be called agent behavior engineering, agentic systems design, or cognitive architecture. We are looking for someone who can help define what this role becomes.

Key Responsibilities

Agent Cognitive Architecture

• Design the reasoning framework for how agents decompose complex ERP tasks into structured decision trees with governance checkpoints at each stage.
• Build agent personas and behavioral profiles for each Rimini Solution domain (Finance, Procurement, Supplier Management, Expense, Support) defining domain-specific reasoning patterns, risk tolerances, and escalation triggers.
• Architect dynamic tool selection strategies where agents choose which MCP tools to invoke based on context, confidence, and task requirements rather than hardcoded sequences.
• Design conversation state management for long-running agent sessions that span multiple interactions, tool calls, and human-in-the-loop approvals.
• Build confidence scoring frameworks that translate LLM output uncertainty into actionable governance decisions (proceed, verify, escape, halt).

Multi-Agent Coordination

• Design A2A (Agent-to-Agent) communication patterns for collaborative workflows where multiple specialized agents contribute to a single business outcome.
• Architect supervisor/worker agent hierarchies wit