Applied AI Engineer – Agentic Systems

Defense Unicorns•Springfield, VA

1d•Hybrid

About The Position

Defense Unicorns is seeking an Applied AI Engineer to embed with a government team and its technology partners building an emerging AI-powered engineering ecosystem. The role focuses on designing, building, and integrating agentic AI capabilities that enable AI models to interact with tools, access enterprise data, execute multi-step workflows, and support mission applications. Work spans LLM integration, agent orchestration, APIs, retrieval-augmented generation (RAG), and connections between AI applications and existing software platforms. This is a hands-on software engineering role for someone who has built agentic AI applications and can quickly learn unfamiliar systems, work directly with commercial technology partners, and address integration, reliability, performance, and security challenges. It is not a traditional AI research or model-development role; the focus is on creating reliable, repeatable agentic capabilities that move beyond experimentation into working software in secure and classified environments. The position requires being local to the National Capital Region and supporting onsite work at a government facility in Springfield, Virginia, approximately 2–3 days per week, with additional onsite presence as mission needs increase. An active Top Secret clearance with SCI eligibility is required; SCI access may be obtained after joining, subject to customer requirements.

Requirements

Approximately 3–5 years of software engineering experience, or equivalent demonstrated technical capability.
Hands-on experience building agentic AI applications, including AI agents, LLM tool calling, multi-step workflows, or agent orchestration.
Strong proficiency with Python and backend software development.
Experience integrating LLMs into applications using APIs, SDKs, or comparable technologies.
Experience building and integrating REST APIs and connecting applications with external services or data sources.
Understanding of agent workflows, tool execution, state management, and error handling.
Experience with Git, testing, debugging, and modern software development practices.
Experience working in cloud-native or containerized environments and collaborating with platform engineering teams.
Ability to troubleshoot application and integration issues across APIs, data services, infrastructure, and AI components.
Ability to work independently, rapidly learn new technologies, and translate ambiguous mission needs into working software.
Active Top Secret clearance with SCI eligibility; SCI access must be obtainable after joining, subject to customer requirements.
Local to the National Capital Region and able to support onsite work in Springfield, VA, approximately 2–3 days per week, with additional onsite presence as mission needs increase.
Relevant agentic AI experience may be demonstrated through professional work, internships, research, open-source contributions, or independent projects.

Nice To Haves

GEOINT experience is preferred but not required.
Experience with agentic AI frameworks such as LangGraph, LangChain, CrewAI, AutoGen, or comparable technologies.
Experience developing multi-agent systems, autonomous workflows, or AI-enabled software development tools.
Experience with Model Context Protocol (MCP), function calling, or other tool integration patterns.
Experience with RAG, embeddings, vector databases, semantic search, or knowledge graphs.

Responsibilities

Design, build, and maintain agentic AI applications that integrate LLMs, tools, APIs, and enterprise data to support mission workflows.
Develop AI agents that execute multi-step tasks, interact with external services, and coordinate actions across existing systems.
Implement agent orchestration, tool calling, workflow state management, error handling, and appropriate human oversight.
Build and integrate RAG pipelines, semantic search, embeddings, and vector-based retrieval for AI application context.
Develop backend services and APIs using Python and modern software engineering practices.
Integrate agentic AI capabilities into existing applications, software delivery workflows, and enterprise platforms.
Establish testing, evaluation, monitoring, and reliability practices for AI agents and LLM-powered applications.
Collaborate with data engineers to ensure agents can access reliable, relevant, and appropriately governed enterprise data.
Work with platform engineers to deploy and operate AI applications in Kubernetes/OpenShift environments and integrate them into CI/CD workflows.
Troubleshoot end-to-end issues involving agent behavior, tool execution, APIs, data access, application services, and infrastructure.
Work directly with government engineers and commercial technology partners to resolve integration challenges and remove blockers to mission delivery.
Develop documentation, reusable components, and operational standards that make successful AI implementation patterns repeatable.
Operate effectively in a fast-moving, ambiguous environment where technologies, security requirements, and mission priorities continue to evolve.
Support onsite work at a government facility in Springfield, VA, approximately 2–3 days per week, with additional onsite presence as mission needs increase.