We are actively seeking a GenAI Engineer Agentic ERP Platform .This role is based in India, Hyderabad.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.Position Summary : - The GenAI Engineer is responsible for building the intelligence layer of Rimini Streets Agentic ERP Platform the AI agents that interact with legacy ERP systems including SAP, Oracle E-Business Suite, and JD Edwards.- This role owns agent development, prompt engineering, context engineering, and LLM orchestration, ensuring that AI agents reason correctly, behave reliably, and deliver value to enterprise users.- Reporting to the Senior Director, Engineering, this engineer designs how agents think, respond, and interact with tools and users.- The role combines deep expertise in LLM behaviour with strong software engineering skills to build production-grade AI systems.- The ideal candidate is passionate about pushing the boundaries of what AI agents can do in enterprise environments while maintaining the reliability and safety that enterprise clients require.Essential Duties & Responsibilities : Agent Development : - Design and develop AI agents using Python and Pydantic AI framework that automate ERP processes and assist enterprise users.- Implement MCP (Model Context Protocol) tool integration, enabling agents to interact with ERP systems, databases, and external services.- Build multi-step agent workflows with decision branching, error recovery, and human-in-the-loop checkpoints using deterministic workflow orchestration.- Develop agent patterns for common enterprise scenarios: data retrieval, transaction processing, approvals, reporting, and advisory tasks.- Implement confidence-based routing to determine when agents should act autonomously vs. escalate to human oversight.- Create and maintain agent evaluation frameworks to measure accuracy, reliability, and task completion rates.Prompt Engineering : - Design and optimize system prompts that define agent personas, capabilities, constraints, and behavioural guidelines.- Develop prompt templates for different task types, incorporating few-shot examples, chain-of-thought reasoning, and structured output formats.- Implement prompt versioning and A/B testing frameworks to systematically improve agent performance.- Create guardrail prompts that enforce policy compliance, prevent harmful outputs, and ensure appropriate tone for enterprise contexts.- Optimize prompts for token efficiency while maintaining response quality and accuracy.- Document prompt patterns, anti-patterns, and best practices for the engineering team.Context Engineering : - Design context window strategies that maximize relevant information while respecting token limits.- Implement dynamic context assembly, selecting and prioritizing information based on task requirements and user state.- Build conversation memory systems that maintain continuity across multi-turn interactions and sessions.- Develop context compression and summarization techniques for long-running conversations.- Integrate retrieved knowledge (from RAG pipelines) with conversation context and system instructions.- Optimize context structure to improve model reasoning and reduce hallucination.LLM Integration & Orchestration : - Integrate with LLMs through LiteLLM gateway, managing model selection, fallbacks, and routing.- Implement streaming responses for real-time user interaction and progressive output rendering.- Build robust error handling for LLM failures, rate limits, and degraded responses.- Develop tool-calling implementations that allow agents to execute actions in ERP systems and external services.- Implement response parsing, validation, and structured output extraction from LLM responses.- Monitor and optimize LLM usage: latency, token consumption, cost, and quality metrics.Guardrails & Safety : - Implement the platforms guardrails architecture: synchronous validation, parallel async checks, and retrospective analysis.- Build input validation to detect prompt injection, jailbreak attempts, and malformed requests.- Develop output guardrails that filter sensitive data, enforce policy compliance, and validate response appropriateness.- Implement audit logging for agent decisions, capturing reasoning traces for compliance and debugging.- Create fallback behaviours for edge cases, ensuring graceful degradation when agents encounter unexpected situations.Experience : - 5-8 years of software engineering experience, with at least 2 years focused on AI/ML or GenAI applications.- Hands-on experience building LLM-powered applications, agents, or chatbots in production environments.- Demonstrated expertise in prompt engineering, including systematic optimization and evaluation.- Experience with AI/ML frameworks and LLM integration patterns.- Strong Python development skills with production-quality code practices.- Experience with API integration and building systems that coordinate multiple services.- Background in enterprise software, ERP systems, or complex business process automation preferred.Technical Skills : Required : - Python expertise with strong understanding of async programming, type hints, and modern Python patterns.- Experience with LLM APIs (Claude, OpenAI, or similar) including streaming, function calling, and structured outputs.- Prompt engineering skills: system prompts, few-shot learning, chain-of-thought, output formatting, and guardrails.- Understanding of context window management, token optimization, and LLM limitations.- Experience with agent frameworks: Pydantic AI, LangChain, LlamaIndex, or similar.- Familiarity with REST APIs, JSON schema, and API integration patterns.- Git version control and collaborative development practices.- Strong debugging skills for AI systems, including analyzing model behavior and failure modes.Preferred : - Experience with Pydantic AI framework for building production AI agents.- Familiarity with MCP (Model Context Protocol) for tool integration.- Experience with LiteLLM or similar LLM gateway/routing tools.- Knowledge of Restate, Temporal, or similar workflow orchestration for agent processes.- Experience building RAG-enhanced applications and integrating retrieved context.- Understanding of vector databases and embedding models (even if not primary implementer).- Experience with evaluation frameworks for LLM applications (RAGAS, LangSmith, or custom).- Familiarity with Claude-specific features: artifacts, computer use, extended thinking.- Knowledge of enterprise security patterns: data masking, PII handling, audit logging.- Exposure to ERP systems (SAP, Oracle EBS) or enterprise business processes.- AI native code development and AI Code Generation tools.Skills & Competencies : - Deep curiosity about LLM behavior; enjoys experimenting with prompts and understanding why models respond the way they do.- Systematic thinker who approaches prompt engineering scientifically with hypotheses, experiments, and measurements.- Strong written communication; prompt engineering requires clear, precise language.- Attention to detail and edge cases; enterprise AI requires handling unexpected inputs gracefully.- Balance of creativity and pragmatism; able to push boundaries while maintaining production reliability.- Collaborative mindset; works effectively with backend engineers, data engineers, and UX designers.- Self-motivated learner who stays current with rapidly evolving GenAI landscape.- Fluent in English (written and verbal) critical for prompt design and documentation.Desired Qualifications : - Bachelors or Masters degree in Computer Science, AI/ML, or related field.- Contributions to open source AI/LLM projects or published work on prompt engineering.- Experience with AI safety, alignment, or responsible AI practices.- Background in NLP, computational linguistics, or conversational AI.- Certifications in AI/ML from major cloud providers or Anthropic/OpenAI.Location & Travel: - Location: Remote, India.- Travel: Minimal; occasional travel for team meetings or training.- Language: Fluent English required (written and verbal) essential for prompt engineering (ref: hirist.tech)