Role Overview

We are looking for a highly accomplished Generative AI Architect to lead the design, development, and deployment of enterprise-scale AI solutions. The ideal candidate will drive AI transformation initiatives by architecting solutions leveraging Large Language Models (LLMs), Agentic AI, RAG (Retrieval-Augmented Generation), Multi-Agent Systems, AI Orchestration Frameworks, and Cloud-Native Platforms.

This role requires a blend of AI architecture, software engineering, cloud architecture, enterprise integration, and stakeholder leadership to deliver creative and scalable Gen AI products.

Key Responsibilities

AI & Solution Architecture

- Define enterprise-wide Generative AI strategy and architecture roadmap.
- Design end-to-end GenAI solutions aligned with business objectives.
- Architect scalable, secure, and production-ready AI platforms.
- Drive architecture governance, design reviews, and technical best practices.

Generative AI & Agentic AI
- Design and implement solutions using GPT, Claude, Gemini, Llama, or equivalent LLMs.
- Architect Agentic AI systems with planning, reasoning, memory, orchestration, and tool execution capabilities.
- Develop AI agents capable of interacting with enterprise applications through APIs and tools.
- Define prompt engineering, evaluation, guardrails, and responsible AI standards.

RAG & Knowledge Systems
- Design Retrieval-Augmented Generation (RAG) architectures.
- Build document ingestion, chunking, embedding, indexing, and retrieval pipelines.
- Implement vector databases and semantic search capabilities.
- Optimize relevance, grounding, and hallucination reduction techniques.





Enterprise Integration
- Integrate AI solutions with enterprise applications, databases, APIs, and business workflows.
- Design MCP (Model Context Protocol) and function-calling frameworks for AI-driven automation.
- Enable conversational AI, intelligent assistants, and business process automation.

Cloud & Platform Engineering
- Architect AI workloads on AWS, Azure, or GCP.
- Design containerized deployments using Kubernetes and Docker.
- Implement CI/CD, MLOps, LLMOps, monitoring, and governance frameworks.
- Ensure scalability, resiliency, observability, and security of AI platforms.

Leadership & Stakeholder Management
- Partner with business leaders to identify and prioritize AI use cases.
- Lead architecture discussions with clients and executive stakeholders.
- Mentor engineering teams and drive AI capability development.
- Provide technical leadership for POCs, pilots, and enterprise implementations.

Required Skills

Generative AI

- Large Language Models (LLMs)
- Generative AI
- Agentic AI
- Multi-Agent Systems
- AI Agents
- Prompt Engineering
- Function Calling
- MCP (Model Context Protocol)
- AI Governance

RAG & AI Frameworks
- RAG Architecture
- LangChain
- LangGraph
- CrewAI
- LlamaIndex
- Semantic Kernel
- Vector Databases

Programming
- Python (Mandatory)
- Java/Spring Boot (Preferred)
- REST APIs
- FastAPI / Flask

Cloud & DevOps
- AWS / Azure / GCP
- Kubernetes
- Docker
- Terraform
- Jenkins / GitHub Actions
- CI/CD Pipelines

Data Technologies
- Pinecone
- Weaviate
- Milvus
- ChromaDB
- Elasticsearch/OpenSearch
- SQL & NoSQL Databases

📌 Technical Architect (Noida)
🏢 Iris Software
📍 Noida