Join Iris Software, recognized as one of India's Top 25 Best Workplaces in IT. We are a rapidly growing IT services company dedicated to being our clients' most trusted technology partner and a premier destination for top industry professionals. With a global presence across India, the U.S.A., and Canada, we empower enterprise clients in financial services, healthcare, transportation, and professional services through technology-enabled transformations. Our expertise spans complex, mission-critical applications leveraging cutting-edge technologies like Application & Product Engineering, Data & Analytics, Cloud, DevOps, Data & MLOps, Quality Engineering, and Business Automation.

At Iris, we believe in fostering a culture where every role is a launchpad for growth. Our "Build Your Future. Own Your Journey." philosophy empowers employees with career ownership and ample opportunities for shaping their paths. We cultivate an environment where your potential is recognized, your voice is heard, and your work makes a tangible impact. Through engaging projects, tailored career development, continuous learning, and mentorship, we support your personal and professional evolution.

Design and develop advanced Generative AI solutions using platforms like Amazon Bedrock, Azure OpenAI Service, and Azure AI Foundry. Define robust AI solution architectures and implementation strategies aligned with business and technical goals. Implement advanced architectures such as Retrieval-Augmented Generation (RAG), Graph RAG, and Agentic AI systems for diverse enterprise use cases. Lead the development of intelligent AI agents, complex tool-calling workflows, and autonomous task execution frameworks. Design and implement multi-agent orchestration solutions using frameworks like LangGraph, exploring emerging tools such as AutoGen or CrewAI.

Optimize prompt strategies, retrieval mechanisms, and response generation frameworks. Develop prompt engineering pipelines, integrate vector databases, and build semantic search solutions. Create scalable AI application development workflows using LangChain or LangGraph. Architect scalable AI engineering solutions incorporating authentication, authorization, asynchronous processing, API governance, and enterprise deployment best practices. Lead initiatives for model fine-tuning and customization to enhance domain-specific AI performance. Establish evaluation frameworks to ensure AI response quality, reliability, and relevance. Design Human-in-the-Loop (HITL) workflows to improve AI governance and business reliability.

This senior engineering role requires 6-8 years of experience, with mandatory expertise in Advanced GenAI & Agentic Framework Concepts, Cloud Application Integration & Deployment, Python, Azure OpenAI Service, Agentic AI Systems, AI Agents & Tool Calling, and LangChain. Experience with platforms such as Amazon Bedrock, Azure AI Foundry, Grog, or AI Search Index is crucial. Proficiency in designing and implementing RAG, Graph RAG, and Agentic AI architectures is essential.

Candidates should possess strong skills in designing multi-agent orchestration solutions using frameworks like LangGraph and evaluating emerging frameworks like AutoGen or CrewAI. Expertise in prompt engineering, vector database integration, semantic search, and designing scalable AI engineering architectures is required. The role also demands experience in leading fine-tuning initiatives, defining AI integration patterns, and establishing evaluation frameworks for AI quality. A proven ability to troubleshoot complex AI challenges, mentor team members, and drive continuous improvement in AI engineering practices is expected. Strong ownership, collaboration, analytical thinking, adaptability, and effective communication are key behavioral competencies for this position.