Generative AI Engineer (Clearance Required)

What You'll Do

• Design and build Generative AI applications using commercial and open-source Large Language Models (LLMs)
• Develop proof-of-concepts that evolve into production-ready software
• Architect Retrieval-Augmented Generation (RAG) solutions using vector databases and enterprise data sources
• Build intelligent agents and AI workflows capable of reasoning, automation, and decision support
• Develop REST APIs and backend services supporting AI applications
• Deploy scalable AI solutions within Microsoft Azure environments
• Design cloud-native architectures using Azure AI Services, Azure OpenAI, Azure Kubernetes Service (AKS), Azure Functions, and Azure Storage
• Build CI/CD pipelines supporting rapid AI deployment and model iteration
• Integrate AI capabilities into existing enterprise applications and mission systems
• Evaluate emerging AI technologies and rapidly prototype new capabilities
• Collaborate with software engineers, cloud architects, data scientists, and mission stakeholders to deliver innovative solutions
• Optimize model performance, latency, scalability, security, and cost
• Implement responsible AI practices, prompt engineering strategies, guardrails, and model evaluation techniques

Requirements

• Active Top Secret Clearance
• 5+ years of software development experience
• 2+ years developing Generative AI or Machine Learning applications
• Strong Python development experience
• Experience working with Large Language Models including GPT, Llama, Claude, Mistral, or similar models
• Experience with prompt engineering and AI workflow development
• Experience building APIs using FastAPI, Flask, or similar frameworks
• Experience deploying cloud-native applications in Microsoft Azure
• Familiarity with containerization technologies including Docker and Kubernetes
• Experience with Git, CI/CD pipelines, and DevSecOps practices
• Strong understanding of software architecture and distributed systems

Preferred Qualifications

• Experience with Azure OpenAI Service
• Experience building Retrieval-Augmented Generation (RAG) systems
• Knowledge of LangChain, LangGraph, Semantic Kernel, LlamaIndex, or similar orchestration frameworks
• Experience with vector databases such as Pinecone, Milvus, pgvector, Azure AI Search, or Chroma
• Experience developing AI agents and autonomous workflows
• Familiarity with MCP (Model Context Protocol) and agent interoperability concepts
• Experience with model evaluation, observability, and prompt optimization
• Experience deploying AI solutions in secure or classified environments
• Familiarity with Infrastructure as Code using Terraform or Bicep
• Knowledge of Azure Machine Learning, Azure AI Foundry, or Azure Cognitive Services