Join Iris Software, a leading IT services company recognized among India's Top 25 Best Workplaces in the IT industry. We are seeking a Senior Engineer to join our Azure AI Platform team and contribute to shaping groundbreaking Generative AI solutions. This is an opportunity to work on complex, mission-critical applications utilizing cutting-edge technologies and to truly own and shape your career success.

At Iris, we foster an award-winning culture that values your talent and ambitions. Our vision is to be our clients' most trusted technology partner and the preferred destination for top industry professionals to realize their full potential. With over 4,300 associates across India, the U.S.A, and Canada, we empower enterprise clients in financial services, healthcare, transportation & logistics, and professional services through technology-enabled transformation.

Design and develop sophisticated enterprise Generative AI solutions leveraging platforms such as Amazon Bedrock, Azure OpenAI Service, Azure AI Foundry, Grog, or AI Search Index. You will define AI solution architectures and implementation strategies aligned with business and technical objectives.

Key activities include designing and implementing Retrieval-Augmented Generation (RAG), Graph RAG, and Agentic AI architectures. You will lead the development of intelligent AI agents, tool-calling workflows, and autonomous task execution frameworks, utilizing frameworks like LangGraph and evaluating emerging options such as AutoGen or CrewAI.

Responsibilities extend to designing and optimizing prompt strategies, retrieval mechanisms, context orchestration, and response generation. This includes building prompt engineering pipelines, integrating vector databases, and developing semantic search solutions for enterprise AI applications. You will also design scalable AI engineering architectures incorporating best practices for authentication, authorization, asynchronous processing, multithreading, API governance, and enterprise deployment.

Lead fine-tuning and model customization for improved domain-specific AI performance. Define AI integration patterns and deployment approaches for enterprise application ecosystems, and design cloud-native AI integration patterns supporting enterprise APIs, databases, messaging platforms, and event-driven architectures. Establish robust evaluation frameworks for AI response quality, reliability, relevance, and consistency.

Design Human-in-the-Loop (HITL) workflows and evaluation mechanisms to enhance AI quality, governance, and business reliability. Review AI solution designs to ensure adherence to engineering standards, scalability, maintainability, and responsible AI practices. Troubleshoot complex AI workflow, retrieval, orchestration, and model behavior challenges through detailed root cause analysis. Mentor team members on GenAI frameworks, RAG architectures, agentic systems, and AI engineering best practices, while driving continuous improvement initiatives focused on AI solution quality, innovation, and operational effectiveness.

This role demands expertise in Retrieval-Augmented Generation (RAG), advanced GenAI concepts, and agentic framework principles. Proficiency in cloud application integration and deployment, agentic AI systems, and specific Azure services such as Azure AI Foundry and Azure OpenAI Service is essential. Experience with AI agents, tool calling capabilities, and frameworks like LangChain is required.

We are looking for individuals who demonstrate strong ownership in driving AI engineering excellence. Effective collaboration with various teams and business stakeholders to ensure smooth delivery is crucial. The ideal candidate will promote innovation and quality-focused engineering through proactive experimentation and continuous improvement.

Additional essential competencies include experience with Amazon Bedrock, Grog, AI Search Index, Graph RAG, LangGraph, and an understanding of emerging frameworks like AutoGen or CrewAI. Skills in prompt engineering, vector database integration, semantic search solutions, and developing RAG architectures for enterprise applications are necessary.

Designing scalable AI engineering architectures is a key requirement, encompassing authentication, authorization, asynchronous processing, scheduling, multithreading, API governance, and enterprise deployment best practices. Experience with fine-tuning and model customization, defining AI integration patterns, and designing cloud-native AI integration patterns is also expected. The ability to establish evaluation frameworks for AI response quality and design Human-in-the-Loop (HITL) workflows is important. Troubleshooting complex AI challenges through root cause analysis and mentoring team members are integral aspects of this role.