AI Engineer

Requisition Number: 106471

AI Engineer

Location

You will have the flexibility to work fully remotely.

• 14,000+ engaged teammates globally
• $8.2 billion in revenue in 2025
• Certified as a Great Place to Work in 9 Countries in 2025
• Fortune 500 Company (No. 447) in 2025
• Received 25+ industry and partner awards in the past year
• $1.4M+ total charitable contributions in 2024 by Insight globally

Now is the time to bring your expertise to Insight. We are not just a tech company; we are a people‑first company. We believe that by unlocking the power of people and technology, we can accelerate transformation and achieve extraordinary results. As a Fortune 500 Solutions Integrator with deep expertise in cloud, data, AI, cybersecurity, and intelligent edge, we guide organizations through complex digital decisions.

As an AI Engineer, you will design and implement production‑grade AI agents and multi‑agent systems that use tools, call APIs, reason over enterprise data, and power modern mobile, web, and Power Platform experiences. We will count on you to be a hands‑on delivery consultant focused on building AI and Agentic AI applications. Along the way, you will get to:

• Design and implement agentic AI systems using Microsoft Foundry (tool/function calling, multi‑step and multi‑agent workflows).
• Build and manage tools and connectors along the agentic chain (MCP‑based tools, custom tool APIs, enterprise integrations).
• Develop RAG and data‑centric AI capabilities using Azure AI/Cognitive Search and other data sources.
• Implement prompt strategies, guardrails, and evaluation loops to improve reliability, safety, and quality.
• Be AmbITious: This opportunity is not just about what you do today but also about where you can go tomorrow. When you bring your hunger, heart, and harmony to Insight, your potential will be met with continuous opportunities to upskill, earn promotions, and elevate your career.

• 6+ years of professional software development, including 2+ years leading technical delivery on client‑facing or cross‑functional projects.
• Hands‑on experience shipping LLM‑powered features to production: tool/function calling, structured outputs, multi‑step or multi‑agent workflows, and the failure modes that come with them.
• Experience building retrieval‑augmented generation pipelines, including chunking, embeddings, hybrid search, and relevance tuning with Azure AI Search or a comparable vector store; familiarity with Foundry IQ and agentic retrieval is a plus.
• Practical experience with evaluation and safety for LLM applications: building eval sets, measuring quality and regressions, and implementing guardrails, content filtering, and prompt‑injection defenses.
• Strong C#/.NET skills building production APIs and services, with the ability to work in Python where the AI tooling demands it.
• Working knowledge of React and Type Script, enough to build and integrate front‑end experiences that consume agentic back ends.
• Experience delivering on Microsoft Azure (App Service or Functions, Storage, Key Vault, Application Insights or equivalent monitoring) and building with Microsoft Foundry, including Foundry Agent Service and Foundry Models.
• Experience designing and integrating tools and connectors for agents, such as MCP servers, custom tool APIs, or enterprise system integrations.
• Comfort operating as a consultant: scoping work with clients, communicating trade‑offs to non‑technical stakeholders, and adapting to different codebases and organizations.

• Experience with Microsoft Agent Framework (the successor to Semantic Kernel and Auto Gen) or comparable frameworks such as Lang Graph, the OpenAI Agents SDK, or the Claude Agent SDK.
• Exposure to Microsoft Power Platform (Copilot Studio, Power…