Agentic AI Manager

About the role:

Marico Limited is expanding its intelligent automation capabilities beyond traditional RPA into the domain of AI agents — systems that can reason, plan, use tools, and complete multi-step business tasks autonomously. We are looking for an Agentic AI lead who can bridge the gap between advanced AI technology and real business problems across Finance, Supply Chain, HR, Sales, R&D, and Procurement. You will design, build, and deploy AI agents on both low-code platforms (Microsoft Copilot Studio, Power Automate, Gemini) and code-first frameworks (Microsoft Agent Framework), integrating them with enterprise systems (SAP, Snowflake, M365). This is a high-visibility role with direct exposure to leadership and the opportunity to shape Maricos Agentic AI architecture from the ground up.

Key Responsibilities:

1. Agent Design & Architecture

• Design end-to-end Agentic AI architectures including single-agent and multi-agent systems using patterns such as ReAct, Reflection Pattern.

• Define agent goals, tools, MCP, memory strategies (in-context, external, semantic, episodic), and failure-handling logic.

• Build agentic RAG systems combining vector search, semantic retrieval, and LLM reasoning for knowledge-grounded responses

• Design human-in-the-loop checkpoints for approval workflows, exceptions, and escalation scenarios

2. Development & Integration

• Build and configure agents on Microsoft Copilot Studio with custom connectors, adaptive cards, and Power Automate flow integrations

• Develop AI agents using Python-based frameworks for code-first builds

• Integrate agents with enterprise APIs: SAP, Snowflake (Cortex), Microsoft Graph API, SharePoint, Teams, and other M365 services etc.

• Implement MCP (Model Context Protocol) servers to expose tools and data sources to agents in a standardized, composable manner

• Build tool-calling layers that allow agents to interact with databases, ERPs, and third-party APIs in real time

3. RAG & Knowledge Management

• Design and implement Retrieval-Augmented Generation (RAG) pipelines: document ingestion, chunking, embedding, vector store indexing, and context-aware retrieval

• Work with vector databases (Pinecone, Azure AI Search, ChromaDB) to build semantic search capabilities for enterprise knowledge bases

• Implement agentic RAG patterns including query routing, self-reflection, and query reformulation for higher-quality responses

4. Evaluation, Testing & Observability

• Build evaluation frameworks to measure agent accuracy, task completion rate, hallucination rate, and latency

• Implement observability and tracing to debug and improve agent behaviour in production

• Define and monitor KPIs for deployed agents; establish feedback loops for continuous improvement

• Conduct structured prompt engineering and system prompt optimization to improve reliability and output quality

5. Governance, Safety & Responsible AI

• Implement guardrails, content filters, and safety mechanisms to ensure agents behave within defined boundaries

• Apply responsible AI principles: fairness, transparency, explainability, and data privacy compliance

6. Collaboration & Stakeholder Management

• Partner with business process owners to translate operational problems into agent design briefs

• Collaborate with vendors in development and adoption of automation

• Present agent capabilities, prototypes, and performance reports to senior leadership including CIO-level audiences

Qualifications:

Mandatory

• 4–6 years of experience in software development, AI/ML engineering, or intelligent automation

• Hands-on experience building at least 5 production-grade AI agent or LLM-powered application/automation

• Strong Python programming skills with demonstrated proficiency in LLM libraries and API integration

• Experience with at least one agent framework

• Understanding of RAG architecture and vector search fundamentals

• Bachelors degree in Computer Science, Engineering, Data Science, or a related technical field

Preferred / Nice-to-Have

• Experience with Microsoft-centric enterprise stacks: M365, Power Platform, Azure, SAP

• Familiarity with RPA tools (UiPath, Power Automate Desktop) and RPA-to-AI agent bridge architectures

• Exposure to multi-agent orchestration patterns (Orchestrator/Worker, CrewAI role-based agents, AutoGen conversations)

• Experience deploying agents in enterprise environments with SSO, data governance, and compliance requirements

• Certifications in Azure AI / Microsoft Copilot / LangChain

• MBA or management background is an advantage for business-facing AI product roles