Join Iris Software, a rapidly expanding IT services company and a recognized Top 25 Best Workplace in India's IT industry. We are seeking a Senior Engineer specializing in Generative AI to contribute to innovative projects and advance your career in an award-winning, growth-oriented culture. At Iris, we empower our associates to own their career journey and shape their success stories while working with cutting-edge technologies.

Our vision is to be the premier technology partner for our clients and a leading destination for top IT professionals. With a global presence spanning India, the USA, and Canada, we deliver transformative technology solutions across financial services, healthcare, transportation, and professional services. Our expertise includes complex application engineering, data and analytics, cloud, DevOps, MLOps, quality engineering, and business automation.

We believe in fostering an environment where your potential is recognized, your voice is heard, and your contributions make a tangible impact. Through challenging projects, personalized development plans, continuous learning, and mentorship, we are committed to supporting your personal and professional growth. Discover the vibrant culture at Iris by watching our employee experience video.

As a Senior GenAI Engineer, you will be instrumental in designing and developing advanced enterprise Generative AI solutions using platforms like Amazon Bedrock and Azure OpenAI Service. You will define AI solution architectures, implementation strategies, and lead the development of complex RAG, Graph RAG, and Agentic AI systems.

Key responsibilities include leading the creation of intelligent AI agents, tool-calling workflows, and autonomous task execution frameworks. You will design and implement multi-agent orchestration solutions using frameworks such as LangGraph, evaluate emerging tools like AutoGen or CrewAI, and optimize prompt strategies, retrieval mechanisms, and response generation.

Furthermore, you will design prompt engineering pipelines, integrate vector databases, develop semantic search solutions, and architect scalable AI engineering platforms incorporating best practices for authentication, authorization, asynchronous processing, and API governance. Fine-tuning models, defining integration patterns, and establishing evaluation frameworks for AI quality and reliability are also crucial aspects of this role. You will troubleshoot complex AI challenges, mentor team members on GenAI technologies, and drive continuous improvement initiatives.

You'll also be responsible for designing scalable cloud-native AI integration patterns, ensuring adherence to engineering standards, and promoting responsible AI practices. Designing Human-in-the-Loop workflows and reviewing AI solution designs to guarantee scalability, maintainability, and ethical considerations will be essential.

We are looking for a Senior Engineer with a strong foundation in Agentic AI Systems, Advanced GenAI, and Agentic Framework Concepts. Proficiency in Cloud Application Integration & Deployment, the FastAPI Framework, Pandas, and Python is essential.

Required skills include expertise in LangGraph, Azure OpenAI Service, AI Agents, and Tool Calling. Experience with Vector Databases and PostgreSQL is highly desirable. You should be adept at designing and implementing enterprise Generative AI solutions using platforms such as Amazon Bedrock, Azure OpenAI Service, Azure AI Foundry, Grog, or AI Search Index.

Candidates must possess the ability to define AI solution architectures and implementation approaches, design and implement RAG, Graph RAG, and Agentic AI architectures, and lead the development of intelligent AI agents and autonomous task execution frameworks. Experience with multi-agent orchestration solutions using frameworks like LangGraph, and the evaluation of emerging frameworks, is expected.

Strong skills in designing and optimizing prompt strategies, retrieval mechanisms, context orchestration, and response generation frameworks are necessary. This includes designing prompt engineering pipelines, vector database integration, semantic search solutions, and Retrieval-Augmented Generation architectures. Experience designing and implementing workflows using LangChain or LangGraph for scalable AI application development is also required.

Candidates should be skilled in designing scalable AI engineering architectures that incorporate authentication, authorization, asynchronous processing, scheduling, multithreading, API governance, and enterprise deployment best practices. Leading fine-tuning and model customization initiatives, defining AI integration patterns and deployment approaches, and designing cloud-native AI integration patterns are key requirements. Establishing evaluation frameworks for AI response quality and designing Human-in-the-Loop workflows are also important.