Job Summary

We are seeking a GenAI Architect to design, architect, and implement enterprise-scale Generative AI solutions. The ideal candidate will have expertise in LLMs, RAG, vector databases, agentic AI frameworks, cloud architecture, and CI/CD, with a robust focus on delivering scalable, secure, and production-ready AI applications.

Key Responsibilities

- Design end-to-end GenAI solutions, including RAG, AI agents, copilots, and multimodal applications.

- Translate business requirements into AI architectures and implementation roadmaps.

- Build and optimize retrieval systems using embeddings, chunking, reranking, and vector search.

- Design agentic workflows using LangChain, LangGraph, MCP, and tool-calling frameworks.

- Define scalable cloud architectures and deployment patterns for AI workloads.

- Implement CI/CD pipelines, containerization, monitoring, and MLOps best practices.

- Ensure security, governance, compliance,



and Responsible AI standards.

Required Skills

- Strong expertise in LLMs, Prompt Engineering, RAG, Fine-tuning, Embeddings, Context Management, and Hallucination Mitigation.

- Experience designing enterprise AI use cases such as copilots, knowledge assistants, intelligent search, summarization, and workflow automation.

- Hands-on experience with vector databases: Pinecone, FAISS, Weaviate, Chroma, Milvus, Azure AI Search, or Elasticsearch Vector Search.

- Experience with LangChain, LangGraph, MCP, Multi-Agent Systems, Memory, Planning, and Guardrails.

- Strong knowledge of cloud platforms (Azure, AWS, or GCP) and AI/ML services.

- Expertise in Docker, Kubernetes, API deployments, CI/CD, DevOps/MLOps, Observability, and Cost Optimization.

📌 GEN AI Architect (Gurugram)
🏢 IRIS SOFTWARE
📍 Gurugram