Shape your career at one of India's top workplaces for IT professionals. Iris Software, a rapidly growing IT services company, offers an award-winning culture where your talent and ambition are highly valued. We are seeking a Senior Engineer to join our Azure AI Platform team, focusing on cutting-edge Generative AI solutions.

Our vision is to be the most trusted technology partner for our enterprise clients, enabling their transformation across financial services, healthcare, transportation, and professional services. We specialize in complex, mission-critical applications using advanced technologies like Cloud, DevOps, Data & Analytics, and MLOps.

At Iris, every role is a launchpad for growth, guided by our philosophy "Build Your Future. Own Your Journey." We foster an environment where your potential is recognized, your voice is heard, and your work makes a significant impact. Through challenging projects, personalized development, and continuous learning, we empower you to achieve your professional and personal best.

Design and develop sophisticated enterprise Generative AI solutions leveraging platforms like Azure OpenAI Service and Azure AI Foundry. Architect AI solutions that align with both business objectives and technical requirements.

Implement advanced architectures, including Retrieval-Augmented Generation (RAG) and Agentic AI, for complex enterprise use cases. Develop intelligent AI agents, define tool-calling workflows, and create frameworks for autonomous task execution.

Orchestrate multi-agent systems using frameworks such as LangGraph and evaluate emerging tools like AutoGen or CrewAI. Optimize prompt strategies, retrieval mechanisms, and response generation for superior performance.

Engineer prompt pipelines, integrate vector databases, and build semantic search solutions for robust AI applications. Design scalable AI architectures incorporating security, asynchronous processing, API governance, and enterprise deployment best practices.

Lead fine-tuning initiatives to enhance domain-specific AI capabilities and define integration patterns for enterprise application ecosystems. Establish comprehensive evaluation frameworks to ensure AI response quality, reliability, and consistency.

Design and implement Human-in-the-Loop (HITL) workflows for continuous AI improvement. Conduct thorough root cause analysis for complex AI challenges and mentor team members on GenAI frameworks and best practices. Drive innovation and operational effectiveness in AI solutions.

This role requires extensive experience with Retrieval-Augmented Generation (RAG), advanced Generative AI concepts, and Agentic Frameworks. Proficiency in Cloud Application Integration & Deployment is essential.

Expertise in Agentic AI Systems, Azure AI Foundry, and Azure OpenAI Service is mandatory. You should be skilled in AI Agents, Tool Calling, and frameworks like LangChain.

Key competencies include designing and implementing RAG, Graph RAG, and Agentic AI architectures. Experience with multi-agent orchestration using LangGraph and evaluating frameworks like AutoGen or CrewAI is crucial.

Demonstrated ability to design and optimize prompt strategies, retrieval mechanisms, and response generation frameworks is expected. Experience with prompt engineering pipelines, vector database integration, and semantic search solutions is vital.

Familiarity with designing scalable AI engineering architectures including authentication, authorization, asynchronous processing, scheduling, multithreading, API governance, and enterprise deployment best practices is required. Experience in leading fine-tuning and model customization initiatives is also important.

Ability to define AI integration patterns and deployment approaches for enterprise application ecosystems. Experience in designing cloud-native AI integration patterns supporting enterprise APIs, databases, messaging platforms, and event-driven architectures is necessary.

Capability to establish evaluation frameworks for AI response quality, reliability, relevance, and consistency. Experience in designing Human-in-the-Loop (HITL) workflows and troubleshooting complex AI workflow challenges through root cause analysis is expected. Mentoring team members on GenAI frameworks and best practices is a key responsibility.