AI Engineer

Job DescriptionJob DescriptionAI Engineer OverviewWe are seeking a hands-on AI Engineer to design, develop, deploy, and maintain mission-critical AI-enabled web applications that address complex, high-impact business challenges.In this role, you will apply modern Generative AI technologies to build production-ready retrieval-augmented generation (RAG) solutions, enterprise knowledge assistants, chatbots, and agentic workflows. You will personally develop Python-based applications, integrate large language models (LLMs) with enterprise data and services, and implement agent and multi-agent workflows that interact with APIs, databases, and external systems.The ideal candidate will have demonstrated experience taking AI solutions beyond prototypes and proof-of-concept implementations into secure, scalable production environments used by real users.You will collaborate with enterprise architects, solutions architects, product owners, AI engineers, data engineers, software engineers, and DevSecOps teams to deliver reliable, maintainable AI applications. Key ResponsibilitiesDesign, develop, deploy, and enhance production-level Generative AI applications and AI-enabled web solutions.Write and maintain Python code to build RAG-based knowledge assistants, chatbots, and agentic AI applications used in production environments.Develop AI applications using Azure AI Foundry, Azure OpenAI, Azure AI Search, Foundry Agent Service, or comparable AWS technologies such as Amazon Bedrock and Amazon OpenSearch.Build end-to-end RAG pipelines, including document ingestion, preprocessing, chunking, embeddings, vector search, retrieval, prompt orchestration, and response generation.Design and implement agent and multi-agent workflows using tool/function calling, structured outputs, state management, guardrails, and human-in-the-loop approvals.Integrate AI applications with REST APIs, enterprise databases, cloud services, internal applications, and MCP-based tools.Develop secure, cloud-native backend services and web applications using Python, application frameworks, containers, and cloud platforms.Implement appropriate authentication, authorization, data protection, and security controls for enterprise AI applications.Evaluate, test, monitor, and optimize AI solutions for accuracy, relevance, groundedness, reliability, latency, performance, and cost.Troubleshoot production AI applications, improve retrieval quality, investigate model-response issues, and implement enhancements.Participate in code reviews, automated testing, CI/CD, technical documentation, and Agile development activities.Collaborate with cross-functional engineering teams to deliver scalable, maintainable AI solutions.Clearly communicate technical designs, implementation decisions, individual contributions, and production deployment approaches.Must-Have Qualifications5+ years of hands-on technical experience in software engineering, web application development, data engineering, data science, machine learning, or a related technical discipline.1+ year of hands-on experience building Generative AI or agentic AI solutions, including LLM APIs, prompt engineering, RAG, tool/function calling, structured outputs, agents, or similar techniques.Demonstrated experience personally writing Python code to develop AI applications, RAG-based knowledge assistants, backend services, or agentic workflows.Hands-on experience developing and deploying AI applications for real users in production environments, beyond coursework, experimentation, or proof-of-concept demonstrations.Practical experience developing RAG applications using document processing, embeddings, vector search, retrieval techniques, and LLM-based response generation.Direct application-development experience with Azure OpenAI and Azure AI Search, or comparable AWS services such as Amazon Bedrock and Amazon OpenSearch.Experience personally implementing agent or multi-agent workflows using tool/function calling to interact with APIs, databases, enterprise systems, or external services.Proficiency in Python and experience developing APIs, backend services, data pipelines, or web applications.Experience with REST APIs, JSON-based interfaces, authentication mechanisms, and external service integrations.Experience with at least one major cloud platform, such as Microsoft Azure or AWS, including deploying or integrating cloud-hosted applications.Understanding of LLM application fundamentals, including tokens, context windows, prompts, model parameters, structured outputs, embeddings, retrieval, and response evaluation.Experience with modern software-development practices and collaboration tools, including Git, GitHub, Jira, pull requests, code reviews, issue tracking, and Agile/Scrum methodologies.Ability to clearly explain individual engineering contributions, technologies used, implementation decisions, and production deployment responsibilities.Ability to obtain and maintain a Public Trust or suitability determination, as required by the client or contract.Bachelor's degree in Computer Science, Engineering, or a related field.Must be a U.S. Citizen or Lawful Permanent Resident (Green Card Holder).Nice-to-Have QualificationsHands-on experience with Azure AI Foundry, Foundry Agent Service, Azure Container Apps, Azure App Service, or related Azure AI services.Experience with containerized or cloud-native application development using Docker, Kubernetes, or similar technologies.Experience implementing Model Context Protocol (MCP) integrations, MCP servers/clients, and agent tool calling.Experience developing multi-agent systems using Microsoft Agent Framework, LangGraph, PydanticAI, or similar frameworks.Experience implementing LLM evaluation, tracing, monitoring, observability, and production performance optimization.Familiarity with CI/CD pipelines, automated testing, cloud deployment, and DevSecOps practices for AI applications.Experience working in federal or state government, healthcare, financial services, or other regulated environments.Exposure to fine-tuning, hosting, or serving open-source LLMs and related model-serving frameworks.Knowledge of AI governance, responsible AI, data privacy, security, and risk-management practices.Experience implementing human-in-the-loop approvals, AI guardrails, prompt-injection defenses, and secure tool access.Strong communication skills and the ability to collaborate with technical and non-technical stakeholders.