Join Iris Software, a rapidly expanding IT services company recognized among India's Top 25 Best Workplaces in the IT industry. We are seeking a Senior Engineer with expertise in Generative AI to contribute to our award-winning culture. At Iris, we empower our professionals to realize their full potential, acting as trusted technology partners for enterprise clients across various sectors. We specialize in complex, mission-critical applications leveraging cutting-edge technologies like Data & Analytics, Cloud, and MLOps.

Our philosophy centers on employee growth, offering a launchpad for careers where individuals own and shape their success. We cultivate an environment that values potential, encourages contributions, and ensures work has a tangible impact. Through advanced projects, personalized development, continuous learning, and mentorship, we are dedicated to fostering both professional and personal advancement for our team members.

Design and implement enterprise-grade Generative AI solutions utilizing platforms such as Amazon Bedrock, Azure OpenAI Service, and Azure AI Foundry. Define robust AI solution architectures and deployment strategies aligned with business and technical goals.

Develop advanced RAG, Graph RAG, and Agentic AI architectures for diverse enterprise use cases. Lead the creation of intelligent AI agents, implement tool-calling workflows, and build autonomous task execution frameworks. Design and deploy multi-agent orchestration solutions using frameworks like LangGraph, evaluating emerging options such as AutoGen and CrewAI.

Optimize prompt strategies, retrieval mechanisms, and response generation frameworks. Engineer prompt pipelines, integrate vector databases, and develop semantic search solutions. Implement scalable AI engineering architectures incorporating security, asynchronous processing, API governance, and enterprise deployment best practices. Lead model fine-tuning initiatives and establish evaluation frameworks for AI response quality and reliability.

Design and implement workflows using LangChain or LangGraph for scalable AI application development. Define AI integration patterns and deployment strategies for enterprise ecosystems. Design cloud-native AI integration patterns for enterprise APIs, databases, and messaging platforms. Troubleshoot complex AI challenges through root cause analysis and mentor team members on GenAI, RAG, and agentic systems.

Proven expertise in advanced GenAI and agentic framework concepts, cloud application integration and deployment, and Python is mandatory. Experience with Azure OpenAI Service, agentic AI systems, AI agents, and tool-calling functionalities is essential.

Key technical skills include proficiency in LangChain and a strong understanding of Retrieval-Augmented Generation (RAG) and Graph RAG architectures. Familiarity with Amazon Bedrock, Azure AI Foundry, Grog, or AI Search Index platforms is required.

Demonstrated ability to design and implement AI solution architectures, including RAG and agentic systems. Experience with prompt engineering, vector databases, and semantic search is crucial. Knowledge of NumPy and Pandas is also necessary.

Candidates should possess strong ownership, collaboration, innovation, and analytical thinking skills. Adaptability to evolving AI technologies and effective communication regarding AI solution design, risks, and opportunities are important. A high attention to detail in AI architecture, prompt design, workflow implementation, testing, and deployment is expected. Experience in mentoring team members and driving continuous improvement in AI engineering practices is a plus.