AI Engineer Agentic AI & Cloud Infrastructure

We are seeking a hands-on AI Engineer to design, develop, and deploy AI agents and intelligent automation solutions for enterprise applications.

The ideal candidate will combine strong software engineering capabilities with practical experience in Microsoft Azure, AI agent development, and enterprise system integrations. This role will focus on building secure, production-ready AI agents that integrate with Microsoft Teams, SharePoint, Outlook, and other Microsoft 365 services.

You will also work with commercial and open-source Large Language Models (LLMs), contributing to model customization, fine-tuning, evaluation, and optimization for specialized business applications.

This position offers end-to-end involvement in the AI development lifecycle, covering agent architecture, backend engineering, cloud infrastructure, authentication, deployment, testing, and production support.

Key Responsibilities

AI Agent Development

• Design, develop, and deploy AI agents capable of executing multi-step tasks and automating enterprise workflows.
• Build AI agents using Microsoft Foundry (Azure AI Foundry), Azure AI Agent Service, LangGraph, Semantic Kernel, or similar frameworks.
• Implement agent capabilities such as tool calling, function execution, Retrieval-Augmented Generation (RAG), memory management, and workflow orchestration.
• Integrate AI agents with internal applications, external APIs, databases, and enterprise systems.
• Develop multi-agent workflows, human-in-the-loop approval processes, and security guardrails.
• Evaluate and optimize agent accuracy, reliability, and performance.

Microsoft Azure & Enterprise Integrations

• Develop and deploy AI agents within Microsoft Teams and other Microsoft 365 applications.
• Integrate AI solutions with Microsoft Graph API to securely access authorized SharePoint, Outlook, OneDrive, Teams, and calendar resources.
• Implement authentication and authorization using Microsoft Entra ID, OAuth 2.0, and Single Sign-On (SSO).
• Work with delegated and application permissions, app registrations, and On-Behalf-Of (OBO) authentication flows.
• Develop backend APIs and services supporting enterprise AI applications.
• Ensure secure data access and appropriate user-level permissions across integrations.

Open-Source LLMs & Model Fine-Tuning

• Work with commercial and open-source LLMs, including Llama, Qwen, and Mistral.
• Fine-tune and customize models for domain-specific applications and enterprise workflows.
• Apply parameter-efficient fine-tuning techniques such as LoRA and QLoRA.
• Prepare training datasets, perform data preprocessing, and develop model evaluation pipelines.
• Experiment with inference optimization, quantization, and model-serving frameworks.
• Evaluate models based on accuracy, latency, scalability, and cost.
• Work with Hugging Face Transformers, PEFT, PyTorch, and related technologies.
• Integrate fine-tuned models into AI applications and agent workflows.

Azure Infrastructure & DevOps

• Provision, configure, and manage cloud infrastructure for AI applications using Microsoft Azure.
• Work with Azure services, including:
• Microsoft Foundry / Azure AI Foundry
• Azure OpenAI Service
• Azure App Service, Azure Functions, and Azure Container Apps
• Azure AI Search
• Azure Storage and database services
• Azure Key Vault
• Azure Monitor and Application Insights
• Microsoft Entra ID
• Build and maintain CI/CD pipelines using Azure DevOps.
• Manage source control, deployments, and environment configurations using Git and Azure DevOps.
• Support Infrastructure as Code (IaC) using Terraform or Bicep.
• Implement monitoring, logging, error handling, and troubleshooting for production AI systems.
• Optimize cloud infrastructure for performance, reliability, security, and cost efficiency.

Required Qualifications

• 2–5 years of experience in software engineering, AI engineering, machine learning engineering, or related technical roles.
• Strong programming proficiency in Python, including backend service and API development.
• Hands-on experience developing LLM-powered applications, AI agents, or intelligent automation systems.
• Experience with agent development frameworks such as Microsoft Foundry Agent Service, LangGraph, Semantic Kernel, or equivalent technologies.
• Working knowledge of RAG, vector databases, embeddings, tool calling, and LLM orchestration.
• Practical experience deploying and managing applications in Microsoft Azure.
• Experience with Azure DevOps, Git, and CI/CD pipelines.
• Understanding of REST APIs, authentication, authorization, and enterprise system integrations.
• Familiarity with Microsoft Entra ID, OAuth 2.0, and Microsoft Graph API.
• Experience working with open-source LLMs and familiarity with model fine-tuning techniques.
• Understanding of model evaluation, inference, and performance optimization.

Preferred Qualifications

• Experience with AWS cloud services and architecture.
• Experience building and deploying AI agents within Microsoft Teams.
• Experience implementing OAuth On-Behalf-Of flows and delegated Microsoft Graph permissions.
• Familiarity with Microsoft 365 Agents SDK, Teams SDK, or Azure Bot Service.
• Hands-on experience fine-tuning open-source LLMs using LoRA, QLoRA, or Hugging Face PEFT.
• Experience deploying open-source models using vLLM, Ollama, Hugging Face, or similar frameworks.
• Familiarity with GPU infrastructure and model inference optimization.
• Experience with Docker, containerized applications, Terraform, or Bicep.
• Knowledge of Model Context Protocol (MCP), multi-agent systems, and agent orchestration.
• Experience integrating AI applications with SharePoint, Dynamics 365, SQL databases, or other enterprise systems.
• Familiarity with enterprise AI security, observability, and MLOps practices.