Get a reply from this employer
Your resume and cover letter, tailored to exactly what they’re hiring for.
Milliman seeks an experienced Full Stack AI Engineer to deliver secure, scalable AI applications and end-to-end agent solutions. You will own delivery from requirements and architecture through implementation, evaluation, deployment, and production support, connecting enterprise knowledge, systems, and APIs.
Role combines modern web development with Generative AI, LLMs, RAG, and MCP, with focus on Azure OpenAI integration and enterprise SaaS style delivery.
About Milliman Independent for over 75 years, Milliman delivers market-leading services and solutions to clients worldwide. Today, we are helping companies take on some of the world’s most critical and complex issues, including retirement funding and healthcare financing, risk management and regulatory compliance, data analytics and business transformation. Through a team of professionals ranging from actuaries to clinicians, technology specialists to plan administrators, we offer unparalleled expertise in employee benefits, investment consulting, healthcare, life insurance, and financial services, and property and casualty insurance.
We are looking for an experienced Full Stack AI Engineer to deliver secure, scalable AI applications and end-to-end agent solutions that automate business workflows. Own delivery from requirements and architecture through implementation, evaluation, deployment, and production support, connecting enterprise knowledge, systems, and APIs. The role combines modern web development with Generative AI, Large Language Models (LLMs), Retrieval-Augmented Generation (RAG), Model Context Protocol (MCP), and Agentic AI frameworks.
Design and develop enterprise Generative AI applications using Azure OpenAI and other LLM services. Build RAG pipelines over SharePoint, databases, documents, and APIs, covering ingestion, chunking, embeddings, vector/hybrid search, and retrieval optimization with Azure AI Search. Develop business-focused AI agents with planning, tool/function calling, and multi‑step workflow execution; integrate enterprise systems through MCP and contribute to orchestration using Microsoft Agent Framework (preferred), LangGraph, or equivalent frameworks. Optimize LLM response quality, latency, token consumption, and operating costs. Implement guardrails, evaluation, observability, and security controls for production AI solutions.
Build responsive, scalable applications with React, TypeScript/JavaScript, HTML, and CSS, including reusable chat interfaces, dashboards, and visualizations. Develop backend services and REST APIs using Python (FastAPI/Flask) and/or C#/.NET. Connect frontends to AI services, enterprise APIs, databases, and backend orchestration; enhance existing applications with AI capabilities. Design modular architectures using microservices and reusable components.
Deploy applications on Azure App Services, Azure Functions, Azure OpenAI, Azure AI Search, and related services. Build enterprise integrations with Azure API Management (APIM), REST APIs, and enterprise integration patterns. Work with Azure SQL, Cosmos DB, PostgreSQL, and structured or unstructured data stores. Build security into design and delivery: enforce authentication, authorization, managed identities, least privilege, role‑based access, and permission‑aware retrieval and tools; verify access boundaries through security reviews and pre‑release testing. Ensure scalability and reliability through logging, monitoring, exception handling, and performance optimization. Develop CI/CD pipelines using Azure DevOps or GitHub Actions.
Promote GitHub Copilot, AI coding agents, and AI-assisted development through reusable prompts and development guidelines that improve engineering productivity. Evaluate emerging AI technologies and frameworks for enterprise adoption.
Partner with business analysts, architects, engineers, and stakeholders to translate requirements into technical designs and deliver production solutions. Contribute to architecture and code reviews; mentor developers and promote engineering best practices and technical standards. Troubleshoot production issues and improve maintainability and reliability.
Bachelor’s degree in Computer Science, Engineering, Information Technology, or related discipline.
5–8 years of full stack software development experience, including building and supporting enterprise production applications.
Hands‑on delivery of Generative AI applications, including practical RAG implementation.