AI Engineer

Washington, DC, United States | Posted on 04/29/2026 AI Developer — Generative AI / LLM Engineering Employment Type: Full-Time - Washington, DC Clearance: Public Trust eligible required About the Role We are placing a Generative AI Developer with a federal agency. This is a hands‑on engineering role focused on moving AI solutions from proof‑of‑concept into secure, scalable production environments. You will design and deploy LLM‑powered applications, RAG pipelines, and agent‑based workflows supporting mission‑critical federal operations. This role is for engineers who have shipped real systems — not just prototypes. Key Responsibilities Design and develop LLM‑powered applications using modern AI frameworks Build and optimize RAG pipelines integrating structured and unstructured data Develop agent‑based AI workflows for automation and decision support Engineer NLP pipelines for classification, summarization, and extraction Build and maintain backend APIs in Python (FastAPI preferred) Deploy to Azure cloud (App Services, AKS, Azure AI Search) Containerize and deploy applications using Docker Implement and maintain CI/CD pipelines Optimize for performance, scalability, and reduced hallucination risk Collaborate cross‑functionally to deliver production‑ready AI solutions Required Qualifications 8+ years of software development experience 3+ years building AI/ML or Generative AI systems Hands‑on LLM experience (OpenAI, Azure OpenAI, or similar) Production API experience — FastAPI preferred Docker and containerized deployments U.S. Citizen or Green Card holder eligible for Public Trust clearance Preferred Qualifications LangChain or Semantic Kernel React or Node.js exposure Prior federal or regulated environment experience Mentorship or architecture leadership #J-18808-Ljbffr