AI Full-Stack Engineer

Responsibilities

• Design, build, and ship full-stack applications from user interface to backend services
• Develop AI-enabled features using LLMs, retrieval-augmented generation (RAG), tool-use agents, and orchestration frameworks
• Integrate AI capabilities into existing enterprise platforms, workflows, and data systems
• Build secure, scalable APIs and services to support AI-powered applications
• Collaborate with product, platform, and security teams to deliver compliant, mission-ready solutions
• Use agentic coding workflows (e.g., Anthropic Claude Code, Google Gemini Code Assist, OpenAI Codex, xAI Grok Code Fast, etc.) to accelerate implementation, testing, and iteration
• Contribute to engineering standards for AI quality, evaluation, observability, and responsible deployment

Qualifications

• Strong experience building and delivering modern full-stack applications
• Proficiency with backend development (Node.js, Python, Java, or similar) and API design
• Frontend experience with React, Next.js, or comparable frameworks
• Practical experience integrating AI/LLM capabilities into software products
• Familiarity with RAG pipelines, vector databases, prompt engineering, and agent toolchains
• Experience working in cloud environments (AWS, Azure, or GCP) with containerized deployments
• Strong engineering fundamentals: testing, version control, CI/CD, and operational reliability

Preferred Qualifications

• Experience deploying AI systems in regulated or enterprise environments
• Familiarity with model evaluation, guardrails, and AI assurance practices
• Exposure to DevSecOps, compliance automation, or secure platform engineering
• Knowledge of orchestration frameworks such as LangChain, LlamaIndex, Semantic Kernel, or custom agent runtimes
• Knowledge of FedRAMP, NIST, or other compliance-driven delivery constraints