Join Iris Software, a rapidly growing IT services company recognized as one of India's Top 25 Best Workplaces in the IT industry. We are seeking a talented Fullstack Gen AI Engineer to contribute to cutting-edge technology solutions.

At Iris, our vision is to be a trusted technology partner for enterprises worldwide. With a global presence and a team of over 4,300 associates, we specialize in areas like Application & Product Engineering, Data & Analytics, Cloud, DevOps, and Generative AI.

We foster a culture where employees are empowered to "Build Your Future. Own Your Journey." Experience personalized career development, continuous learning, and mentorship in a dynamic and impactful environment.

Develop and deploy advanced Generative AI solutions using platforms such as Azure OpenAI Service and Azure AI Foundry. Build sophisticated RAG, Graph RAG, and Agentic AI systems to enhance enterprise knowledge retrieval and intelligent automation.

Create AI-powered applications with LLMs that align with business objectives. Implement secure AI services using Python and FastAPI, ensuring robust API design with asynchronous capabilities, request throttling, and multithreading.

Configure and integrate AI agents, tool-calling mechanisms, and intelligent workflows with LangChain or LangGraph. Master prompt engineering, context management, and retrieval strategies for optimal AI response quality.

Support fine-tuning and model customization for domain-specific use cases. Integrate AI applications with enterprise systems, databases, and cloud services. Perform comprehensive testing, validation, and monitoring of AI solutions.

Maintain detailed technical documentation and collaborate with cross-functional teams to ensure successful AI solution delivery. Focus on developing reliable, scalable, and maintainable AI solutions.

We are looking for an engineer proficient in advanced GenAI and Agentic Framework concepts, Cloud Application Integration & Deployment, AI Agents & Tool Calling, Azure AI Foundry, Agentic AI Systems, LangChain, and LangGraph. Familiarity with GitHub is also essential.

Key responsibilities include developing and implementing Generative AI solutions, building RAG and Agentic AI systems, and creating AI-powered applications leveraging LLMs. Proficiency in Python and FastAPI for secure AI service development, along with experience in configuring AI agents and workflows using LangChain/LangGraph, is crucial.

Skills in prompt engineering, context management, and retrieval strategies are vital. Experience with vector databases, semantic search, fine-tuning, and model customization is highly valued. The role also requires integrating AI applications with enterprise systems and ensuring the quality, accuracy, and reliability of AI outputs through testing and monitoring.