Azure Agentic Ai Architect

Job Description

We are seeking a seasoned Azure AI Architect with deep expertise in Azure Generative AI, LLM-based solutions, and agentic AI systems. The ideal candidate brings 12-15 years of experience in AI/ML engineering and architecture, 2 years of experience on Generative/ Agentic AI, strong leadership capabilities, and hands-on experience designing and deploying production-grade AI solutions on Azure. This role combines strategic architecture ownership with hands-on technical leadership.

Roles & Responsibilities

AI Architecture & Technical Leadership

Define and own the Azure AI architecture roadmap for GenAI, search, recommendation, and agentic AI solutions.

Design scalable, secure, and cost-optimized AI architectures using Azure-native services.

Provide technical leadership and mentorship to AI/ML engineers and data scientists.

Partner with business and engineering leaders to align AI initiatives with enterprise objectives.

Azure Generative AI & Agentic AI

Architect and deliver Generative AI solutions using Azure OpenAI, Azure AI Foundry, and Azure AI Services.

Design and implement agentic AI workflows using LangChain, LangGraph, and tool/function calling patterns.

Build autonomous and semi-autonomous agents capable of reasoning, planning, and orchestration.

Establish best practices for prompt engineering, evaluation, monitoring, and governance.

LLMs, APIs & Application Integration

Integrate LLMs into enterprise applications using Azure Functions, REST APIs, and event-driven architectures.

Implement secure, scalable API layers for AI services with authentication, throttling, and observability.

Drive adoption of LLMOps practices including prompt versioning, model monitoring, and feedback loops.

Search, Retrieval & Data Platforms

Architect RAG-based solutions using Azure AI Search (Cognitive Search), Cosmos DB, and vector stores.

Design semantic search, ranking, and recommendation pipelines for high-quality user experiences.

Implement real-time and batch feedback loops to continuously improve relevance and accuracy.

MLOps, Security & Responsible AI

Define end-to-end ML/GenAI lifecycle architecture: ingestion, orchestration, deployment, monitoring.

Leverage Azure-native DevOps and CI/CD pipelines for AI workloads.

Ensure compliance with Responsible AI, data governance, security, and enterprise standards.