• Design and develop AI agents and multi-agent workflows for enterprise use cases.

- Implement agent logic, orchestration flows, tool usage, and API-driven task execution.
- Build AI agents capable of handling task execution, workflow automation, and contextual interactions.
- Design, test, and optimize prompts, system instructions, and reusable prompt templates.
- Improve response quality, grounding, hallucination control, and output reliability.
- Implement fallback logic, retry mechanisms, and basic human-in-loop workflows.
- Implement Retrieval Augmented Generation (RAG) pipelines using enterprise data sources.
- Work with embeddings, vector databases, chunking strategies, and semantic search techniques.
- Support development of context-aware AI solutions integrating structured and unstructured data.
- Develop and integrate backend services and APIs for AI-based applications.
- Enable AI agents to interact with enterprise systems such as CRM, policy systems, workflow tools, and databases.
- Build scalable microservices to support AI solution deployment.
- Develop or integrate frontend interfaces such as chat-based UI, dashboards, or workflow interfaces for AI applications.
- Ensure seamless user experience for AI-powered applications.
- Optimize latency, response time, and performance of AI workflows.
- Monitor token usage, API performance, and system reliability.
- Support implementation of logging, performance monitoring, and evaluation mechanisms.
- Leverage AI-assisted development tools such as GitHub Copilot, Cursor, and enterprise copilots to enhance productivity.
- Contribute to reusable components, accelerators, and AI engineering best practices.
- Ensure adherence to enterprise standards for coding, security, and governance.



Measures of Performance:
- Successful development and deployment of AI agents and workflows for assigned use cases.
- Quality and reliability of AI outputs (accuracy, grounding, reduced hallucinations).
- Adherence to performance benchmarks (latency, response time, and system stability).
- Efficiency in backend and frontend integration of AI solutions with enterprise systems.
- Effective implementation of RAG pipelines and data integration for contextual AI responses.
- Code quality, reusability of components, and contribution to shared AI engineering assets
- Adoption of AI-assisted development practices in day-to-day engineering work
- Timely delivery of use cases and responsiveness to business requirements
- Compliance with defined AI governance, security, and engineering standards

Key Responsibilities:

• Good understanding of LLMs, GenAI, and Agentic AI concepts, including multi-agent workflows.

- Hands-on experience with frameworks such as LangChain, LangGraph, CrewAI, AutoGen, or similar.
- Working knowledge of RAG pipelines, embeddings, vector databases, and semantic retrieval techniques.
- Solid experience in backend engineering using Python, FastAPI, REST APIs, and microservices architecture.
- Experience in frontend development (React, Angular, or similar) for building AI application interfaces.
- Familiarity with Azure OpenAI or similar LLM platforms and enterprise API integrations.
- Understanding of system integration, API orchestration, and enterprise application connectivity.
- Basic understanding of AI observability, monitoring, and token optimization.
- Awareness of security, governance, and responsible AI practices.
- Strong problem-solving ability and execution focus with attention to performance and scalability.

📌 IT - Manager - Agentic AI (Gurugram)
🏢 PNB Metlife
📍 Gurugram