AI Engineer (Washington DC Metro Area)

We are looking for an AI Engineer to build production generative AI applications that help federal clients find information, make decisions, and get work done faster. Azure AI is central to this position: the engineer will independently design, build, evaluate, and troubleshoot retrieval-based knowledge assistants, chatbots, and agentic workflows using Azure OpenAI and Azure AI Foundry. The role involves close collaboration with architects, product owners, data engineers, and DevSecOps teams to turn emerging AI capabilities into secure, scalable, and maintainable web applications. Federal Compliance • Identity verification will happen at multiple stages of the interview process to adhere to federal compliance • This role is based in the US for a US work-authorized person Required • Must be a U.S. citizen or green card holder • Strong preference for candidates based in Washington, DC. Atlanta, Georgia will also be considered • 5+ years of hands-on experience in software engineering, web application development, data engineering, data science, machine learning, or a similar technical field • 1+ years of hands-on experience building generative AI or agentic AI solutions (LLM APIs, prompt engineering, tool/function calling, structured outputs, RAG, or agents) • Python experience building applications, backend services, data pipelines, and web applications • Experience with REST APIs, JSON interfaces, authentication, and third-party service integrations • Experience deploying or integrating applications on a major cloud platform (Microsoft Azure or AWS) • Solid grasp of LLM fundamentals: tokens, context windows, system and user prompts, model parameters, embeddings, retrieval, and evaluating model responses • Experience with Git, GitHub, Jira, pull requests, code reviews, and Agile/Scrum delivery • Bachelor's degree in computer science, engineering, or a related field • Ability to pass a background check and obtain a public trust security clearance Key Responsibilities • Build and improve production generative AI applications and web-based AI solutions. • Develop AI applications using Azure AI Foundry, Azure OpenAI, and Foundry Agent Service. • Build retrieval-augmented generation (RAG) systems, knowledge assistants, chatbots, and agentic workflows. • Implement agent and LLM workflows that use tools, structured outputs, guardrails, and human review where needed. • Integrate AI applications with APIs, enterprise data sources, databases, cloud services, and MCP-based tools. • Develop secure, cloud-native services and user interfaces using Python, web frameworks, containers, and Azure services. • Test, evaluate, and monitor AI applications to improve quality, reliability, latency, and cost. • Collaborate with AI engineers, software engineers, architects, and DevSecOps teams to deliver maintainable production applications. Nice to Haves: • Experience with containerized or cloud-native development (Docker, Azure Container Apps, Azure App Service) • Experience with Model Context Protocol (MCP) integrations and hands-on development of multi-agent systems • Experience with AI agent frameworks (Microsoft Agent Framework, LangGraph, PydanticAI) • Experience implementing LLM evaluation, tracing, monitoring, and observability • Experience with CI/CD and automated testing for AI applications • Experience in government, healthcare, or other regulated environments • Exposure to fine-tuning, hosting, or serving open-source LLMs • Knowledge of AI governance, responsible AI principles, and related security and risk practices