Azure AI Engineer – Generative AI / LLM

ob Overview

We are looking for an experienced Azure AI Engineer to design, build, deploy, and optimize production-ready AI and Generative AI solutions using Microsoft Azure.

You will work with Azure AI Foundry, LLMs, Prompt Flow, RAG, AI Agents, Azure AI Search, Python, APIs, and cloud-native architectures to integrate intelligent capabilities into enterprise applications.

This role is ideal for AI/ML Engineers and Software Engineers with hands-on experience building LLM-powered applications in production and a strong interest in enterprise GenAI.

Key Responsibilities

• Design, develop, and deploy AI/LLM-powered applications and end-to-end AI pipelines.
• Build production-ready Generative AI solutions using Azure AI services.
• Develop Prompt Flows, orchestration pipelines, and agent-based AI workflows.
• Design and implement Retrieval-Augmented Generation (RAG) solutions.
• Work with embeddings, chunking strategies, indexing, and context management.
• Integrate AI capabilities into applications through REST APIs and cloud-native architectures.
• Use Azure AI Foundry for model deployment, inference, orchestration, and optimization.
• Implement search and retrieval solutions using Azure AI Search, including hybrid retrieval.
• Monitor and optimize AI model performance, accuracy, scalability, reliability, and cost.
• Establish observability, logging, monitoring, and performance measurement for AI systems.
• Implement secure-by-design practices covering identity, access control, networking, and data protection.
• Apply Responsible AI principles covering model safety, governance, explainability, and compliance.
• Collaborate with Data Engineers, Software Engineers, Product Teams, and business stakeholders.
• Translate business requirements into practical AI solutions and define guardrails, KPIs, and success criteria.

Requirements

• 3–6+ years of experience in AI/ML, software engineering, or cloud-based AI solution development.
• Hands-on experience building and deploying AI/LLM-powered applications in production.
• Strong experience with Azure or other major cloud platforms such as AWS or GCP.
• Hands-on experience with Generative AI, Prompt Engineering, RAG, AI Agents, or LLM applications.
• Strong programming experience in Python.
• Experience developing REST/JSON APIs and microservices.
• Knowledge of CI/CD and modern software engineering practices.
• Experience with Azure AI Foundry, model deployment, and inference APIs.
• Experience with Azure AI Search, embeddings, indexing, chunking, and hybrid retrieval.
• Knowledge of Azure networking and Microsoft Entra ID.
• Understanding of AI observability, security, governance, and Responsible AI.
• Experience with Copilot Studio and Power Platform is an advantage.

Technical Skills

AI / GenAI

• Generative AI / LLMs
• Prompt Engineering
• Prompt Flow
• RAG
• AI Agents
• Orchestration
• Embeddings
• Vector / Hybrid Search

Azure AI

• Azure AI Foundry
• Azure AI Search
• Model Deployment
• Inference APIs
• Microsoft Entra ID
• Azure Networking
• Azure Observability

Software Engineering

• Python
• REST APIs / JSON
• Microservices
• CI/CD
• Cloud-Native Architecture

Additional Advantage

• Copilot Studio
• Microsoft Power Platform
• Responsible AI / AI Governance

What We're Looking For

• Strong analytical and problem-solving abilities.
• Ability to translate complex business problems into practical AI solutions.
• Comfortable working in ambiguous and rapidly evolving AI environments.
• Strong communication skills, especially when explaining probabilistic AI outputs to non-technical stakeholders.
• Ability to work effectively across Engineering, Data, Product, and Business teams.
• Ability to establish appropriate AI guardrails, KPIs, and success criteria.