Join Iris Software, recognized among India's Top 25 Best Workplaces in IT, and be part of a rapidly growing IT services company. We are seeking a Technical Architect to lead the design and deployment of enterprise-grade Generative AI and Agentic AI solutions. This role offers a unique opportunity to own the technical vision from inception to production, contributing to cutting-edge projects.

At Iris, we empower our associates with "Build Your Future. Own Your Journey.", fostering a culture that values your potential and amplifies your impact. We provide continuous learning, mentorship, and exciting projects to support your professional and personal growth.

Design comprehensive GenAI, RAG, Agentic AI, and multi-agent architectures. Define solution patterns including LLMs, vector databases, orchestration, APIs, data pipelines, and enterprise integrations. Architect AI agents with advanced capabilities like tool/function calling, workflow orchestration, and memory management. Evaluate and select optimal foundation models and AI platforms based on quality, latency, security, and cost. Develop solutions leveraging cloud AI ecosystems such as Azure OpenAI, Amazon Bedrock, or Google Vertex AI. Establish robust LLMOps, evaluation, observability, guardrails, and Responsible AI practices. Ensure all architectures meet enterprise requirements for security, privacy, resilience, scalability, compliance, and cost optimization. Lead architecture workshops, technical design reviews, and PoCs, while creating reference architectures and reusable accelerators for GenAI adoption.

Proven expertise in Generative AI, LLMs, Agentic AI, and AI solution architecture is essential. Hands-on experience with RAG, embeddings, vector search, and semantic retrieval is required. Familiarity with agent frameworks like LangGraph, LangChain, Microsoft Agent Framework, Semantic Kernel, or Bedrock Agents/AgentCore is necessary. A strong understanding of multi-agent orchestration, tool calling, context engineering, memory, and Human-in-the-Loop patterns is expected. Experience with at least one major cloud AI ecosystem (Azure, AWS, or GCP) is mandatory. Proficiency in Python, REST APIs, microservices, and distributed/cloud-native architectures is crucial. Experience with LLM evaluation, tracing, monitoring, prompt/model versioning, and LLMOps/MLOps is needed. Understanding of AI security, guardrails, Responsible AI, identity/access management, and data governance is important. The ability to assess architectural trade-offs across accuracy, latency, scalability, reliability, and cost is a key requirement.