I

iSupport Worldwide

AI Engineer - Agentic AI & Cloud Infrastructure

AI Application Engineering +1Confirmed live in the last 24 hours
Full-timeRemote in PhilippinesNo salary listedRemote

About the Job

Requirements

  • The role requires 2–5 years of experience in software engineering, AI engineering, machine learning engineering, or related technical roles.
  • The candidate must have strong Python programming proficiency and experience developing backend services and APIs.
  • The candidate must have practical experience developing large language model-powered applications, AI agents, or intelligent automation systems.
  • The candidate must have experience with agent frameworks such as Microsoft Foundry Agent Service, LangGraph, Semantic Kernel, or equivalent tools.
  • The candidate must have working knowledge of retrieval-augmented generation, vector databases, embeddings, tool calling, and large language model orchestration.
  • The candidate must have hands-on experience with Microsoft Azure, including deploying and managing cloud applications.
  • The candidate must have experience using Azure DevOps, Git, and continuous integration and continuous delivery pipelines.
  • The candidate must understand REST APIs, authentication, authorization, and enterprise system integrations.
  • The candidate must be familiar with Microsoft Entra ID, OAuth 2.0, and Microsoft Graph API.
  • The candidate must have experience working with open-source large language models and familiarity with model fine-tuning techniques.
  • The candidate must understand model evaluation, inference, and performance optimization.

Responsibilities

  • Design, develop, and deploy AI agents capable of performing multi-step tasks and automating business workflows.
  • Build agents using Microsoft Foundry (Azure AI Foundry), Azure AI Agent Service, and agent frameworks such as LangGraph, Semantic Kernel, or similar technologies.
  • Develop agent capabilities including tool calling, function execution, retrieval-augmented generation, memory management, and workflow orchestration.
  • Integrate agents with internal applications, external APIs, databases, and enterprise systems; implement multi-agent workflows, human-in-the-loop approvals, and appropriate security guardrails.
  • Test, evaluate, and optimize agent accuracy, reliability, and performance.
  • Build and deploy AI agents that operate within Microsoft Teams and other Microsoft 365 applications.
  • Integrate AI agents with Microsoft Graph API to access authorized resources such as SharePoint, Outlook, OneDrive, Teams, and calendars.
  • Implement secure authentication and authorization using Microsoft Entra ID (Azure AD), OAuth 2.0, and single sign-on.
  • Work with delegated permissions, application permissions, app registrations, and On-Behalf-Of authentication flows.
  • Develop backend APIs and services to support agent interactions with enterprise applications, ensuring secure data access and appropriate user-level permissions across integrations.
  • Work with commercial and open-source or open-weight large language models, including Llama, Qwen, and Mistral.
  • Fine-tune and customize large language models for domain-specific applications, enterprise workflows, and specialized tasks.
  • 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 and compare open-source and commercial large language models based on accuracy, latency, scalability, and cost.
  • Work with frameworks and libraries such as Hugging Face Transformers, PEFT, PyTorch, and related tools.
  • Support deployment and integration of fine-tuned models into AI applications and agent workflows.
  • Provision, configure, and manage cloud infrastructure for AI applications within Microsoft Azure, including Microsoft Foundry / Azure AI Foundry, Azure OpenAI Service, Azure App Service, Azure Functions, Azure Container Apps, Azure AI Search, Azure Storage and database services, Azure Key Vault, Azure Monitor and Application Insights, and Microsoft Entra ID.
  • Build and maintain continuous integration and continuous delivery pipelines using Azure DevOps.
  • Manage source control, deployments, and environment configurations using Git and Azure DevOps.
  • Support infrastructure as code using Terraform or Bicep.
  • Implement monitoring, logging, error handling, and troubleshooting for production AI systems.
  • Optimize cloud infrastructure for performance, reliability, security, and cost.

Desired 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.
  • Experience with Microsoft 365 Agents SDK, Teams SDK, or Azure Bot Service.
  • Hands-on experience fine-tuning open-source large language models using LoRA, QLoRA, or Hugging Face PEFT.
  • Experience deploying open-source models using vLLM, Ollama, Hugging Face, or similar serving frameworks.
  • Familiarity with GPU infrastructure and model inference optimization.
  • Experience with Docker, containerized applications, Terraform, or Bicep.
  • Familiarity with Model Context Protocol, 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.

About the Company

iSupport Worldwide

Company size
Not listed
Company stage
Not listed
Total funding
Not listed
Headquarters
Not listed
Founded
Not listed

Recently Posted Jobs

Explore more opportunities at iSupport Worldwide

See more jobs