Generative AI Applications Engineer (Agents & RAG)

Role Overview

You'll turn mission needs into secure, reliable, and scalable GenAI applications no model training required. This is a hands-on role across agentic workflows, RAG, prompt/policy design, LLM evaluation, and platform integration. You'll own the end-to-end path from use case evaluation → production deployment → operational excellence, partnering with product, security, data, and SRE to ship features safely and at scale.

What You'll Do (Day to Day)

• Design & build agentic workflows and Retrieval-Augmented Generation (RAG) pipelines for high-stakes federal use cases.
• Develop and maintain prompt templates, system policies, and guardrails to ensure safety, accuracy, and compliance.
• Evaluate LLM outputs using both automated metrics and human feedback loops; iterate on quality, latency, and cost.
• Integrate GenAI services into existing platforms via APIs, microservices, and orchestration layers.
• Collaborate with product managers to define use cases, success criteria, and rollback strategies.
• Work with security and data teams to ensure data isolation, auditability, and access controls.
• Participate in on-call rotation and contribute to post-incident reviews for production AI systems.