Join Iris Software, a recognized Top 25 Best Workplace in India's IT industry, and embark on a journey to create your best work. We are a rapidly expanding IT services company dedicated to empowering our clients through technology-driven transformations.

Our vision is to be the premier technology partner for enterprises, fostering an environment where top talent can reach their full potential. With a global presence across India, the U.S.A., and Canada, we specialize in complex, mission-critical applications leveraging cutting-edge technologies. We focus on areas such as Application & Product Engineering, Data & Analytics, Cloud, DevOps, Data & MLOps, Quality Engineering, and Business Automation.

At Iris, we believe in providing a launchpad for your career. Our culture champions ownership, values your voice, and ensures your work makes a significant impact. Through challenging projects, personalized development, continuous learning, and mentorship, we support your professional and personal growth.

Design and deploy advanced Generative AI solutions utilizing platforms like Amazon Bedrock, Azure OpenAI Service, and AI Search. Define comprehensive AI solution architectures and implementation strategies aligned with business goals.

Develop and implement RAG, Graph RAG, and Agentic AI architectures for enterprise-grade applications. Lead the creation of intelligent AI agents, tool-calling frameworks, and autonomous task execution systems.

Orchestrate multi-agent solutions using frameworks such as LangGraph, and explore emerging platforms like AutoGen or CrewAI. Optimize prompt strategies, retrieval mechanisms, and response generation frameworks for maximum efficiency.

Design and implement prompt engineering pipelines, vector database integrations, and semantic search solutions. Develop scalable AI application architectures incorporating authentication, authorization, asynchronous processing, and enterprise deployment best practices.

Lead fine-tuning and model customization efforts to enhance domain-specific AI performance. Define integration patterns and deployment strategies for complex enterprise application ecosystems, including cloud-native approaches.

Establish robust evaluation frameworks for AI response quality, reliability, and consistency. Design Human-in-the-Loop (HITL) workflows to improve AI governance and business reliability.

Conduct detailed root cause analysis to resolve complex AI workflow and model behavior challenges. Mentor team members on GenAI, RAG, agentic systems, and AI engineering best practices. Drive continuous improvement initiatives focused on AI quality and innovation.

We are seeking a skilled Senior Engineer with expertise in Advanced GenAI and Agentic Framework Concepts, Cloud Application Integration and Deployment, and Azure OpenAI Service.

Key technical proficiencies include AI Agents, Tool Calling, and LangChain. Experience with platforms such as Amazon Bedrock, Azure AI Foundry, Grog, and AI Search Index is essential.

Candidates should be adept at designing and implementing Retrieval-Augmented Generation (RAG), Graph RAG, and Agentic AI architectures. Experience with multi-agent orchestration using frameworks like LangGraph, AutoGen, or CrewAI is highly valued.

Proficiency in designing prompt engineering pipelines, vector database integrations, and semantic search solutions is required. The role also involves designing scalable AI engineering architectures with considerations for authentication, authorization, asynchronous processing, and API governance.

Experience with fine-tuning models, defining AI integration patterns, and establishing AI response quality evaluation frameworks is expected. A strong ability to troubleshoot complex AI challenges and mentor team members on GenAI frameworks and best practices is crucial.