Join Iris Software, a rapidly expanding IT services firm recognized among India's Top 25 Best Workplaces in the IT industry. We are seeking a visionary GenAI Architect to spearhead the design and implementation of cutting-edge Generative AI solutions across diverse enterprise applications.

This role demands extensive hands-on experience and architectural acumen in Large Language Models (LLMs), Retrieval Augmented Generation (RAG), vector databases, and agentic AI frameworks. Proficiency in cloud-native deployments and CI/CD automation is essential. You will collaborate closely with business stakeholders, data/ML teams, and engineering departments to develop scalable, secure, and production-ready GenAI platforms and applications, driving technological transformation for our global enterprise clients.

As a GenAI Architect, you will craft end-to-end Generative AI solutions, including sophisticated RAG pipelines, agentic workflows, and multimodal use cases. You will translate complex business challenges into actionable GenAI-driven strategies, providing detailed solution blueprints and implementation roadmaps.

Key duties include designing and implementing robust retrieval systems using advanced techniques such as embeddings, chunking strategies, and metadata filters. You will select, integrate, and optimize vector databases for performance and relevance, and build advanced agentic systems utilizing frameworks like LangChain and LangGraph. Furthermore, you will define scalable and secure cloud architecture patterns for GenAI deployments, drive productionization via CI/CD pipelines and containerization, and champion responsible AI practices.

Your leadership will extend to providing technical guidance, conducting reviews, and mentoring engineering teams. You will ensure solutions align with project timelines and business objectives through close collaboration with product and delivery teams. Experience with cloud components supporting AI/ML solutions and managed services is preferred.

We are looking for a candidate with deep expertise in GenAI/LLM Architecture and Algorithms, possessing strong knowledge of LLM concepts, prompting techniques, fine-tuning versus RAG, embeddings, context windows, token limits, and hallucination control. Proven experience designing enterprise GenAI use cases, such as document Q&A, copilots, summarization, search, workflow automation, customer support, and knowledge assistants, is required.

Proficiency in Vector Databases and Retrieval Systems is crucial, including hands-on understanding of concepts like embeddings, indexing, ANN search, hybrid search, and metadata filtering. Experience with tools such as Pinecone, FAISS, Weaviate, Chroma, Milvus, Azure AI Search, or Elastic (vector) is expected.

Strong working knowledge of Agentic AI Frameworks, including LangChain, LangGraph, MCP, tool/function calling, memory management, planning, multi-agent workflows, and guardrails, is essential. Additionally, experience with Cloud Architecture & Deployments for GenAI workloads, covering compute, networking, storage, IAM/security, and logging/monitoring, is required. Familiarity with CI/CD and Productionization, including Docker, Kubernetes, API deployment, model endpoint integration, and DevOps/MLOps practices, is also a must-have.