Data & AI Engineer (Agentic Systems)
Posted 4 days ago
The role in short
Embed with government teams to design, build, and integrate production agentic AI applications and RAG pipelines using Python and LLMs.
Role Description
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.
This role will focus on designing, building, and integrating agentic AI capabilities that allow AI models to interact with tools, access enterprise data, execute multi-step workflows, and support mission applications. The engineer will work across LLM integration, agent orchestration, APIs, retrieval-augmented generation (RAG), and the interfaces between AI applications and existing software platforms.
The ideal candidate is a hands-on software engineer with demonstrated experience building agentic AI applications. They should be comfortable entering an evolving architecture, learning unfamiliar systems quickly, working directly with commercial technology partners, and solving difficult problems involving integration, reliability, performance, and security.
This is not a traditional AI research or model development role. The focus is on building reliable, repeatable agentic capabilities that move beyond experimentation into working software in secure and classified environments.
Responsibilities
- Design, build, and maintain agentic AI applications that integrate LLMs, tools, APIs, and enterprise data to support mission workflows.
- Develop AI agents capable of executing multi-step tasks, interacting with external services, and coordinating 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 to provide relevant context for AI applications.
- 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 within 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.
Local to the National Capital Region and able to support onsite work at a government facility in Springfield, VA as mission needs increase.
Clearance & Travel
- Active Top Secret clearance with SCI eligibility required
- Ability to support approximately 2–3 days per week onsite in Springfield, VA, with additional onsite presence as mission needs increase.
Minimum Experience and Qualifications
- 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.
- GEOINT experience is preferred, not required.
Relevant agentic AI experience may be demonstrated through professional work, internships, research, open-source contributions, or independent projects.
Preferred Experience and Qualifications
- 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.
Mission Focus
Make trusted data available where AI needs it, while establishing the repeatable, secure data patterns required to move from experimentation to operational capability.
Prep for this interview
5 questions likely to come up at Defense Unicorns, each matched to a line in this posting.
- 1LLMs, RAG and agents
They wrote: “Hands-on experience building agentic AI applications, including AI agents, LLM tool calling, multi-step workflows, or agent orchestration.”
A customer wants a chatbot over their internal documents. How do you build it?
How to answer
Why they ask: RAG is the most common first project. They want the whole path, from messy files to answers people trust.
- Collect and clean the documents; handle permissions per user
- Split them into chunks, embed, and store with source links
- Retrieve, then answer with citations; say “I don't know” when retrieval is weak
- Build a test set of real questions with expected answers before launch
Tip: Spend more time on the data and on testing than on the model.
- 2Integrations and APIs
They wrote: “Ability to troubleshoot application and integration issues across APIs, data services, infrastructure, and AI components.”
Walk me through connecting our product to a customer's internal system that has no documentation.
How to answer
Why they ask: This happens weekly in the job. They want a calm, step-by-step method.
- Find who owns the system and get read access to a test environment
- Watch real traffic or logs to learn the data shapes
- Build a thin adapter with logging around every call
- Agree on how failures get reported, and who fixes what
Tip: Talk about finding the owner of the system first. The code is the easy part.
- 3Coding
They wrote: “Develop backend services and APIs using Python and modern software engineering practices.”
Here's a CSV export from a customer. Write a script that cleans it and loads it into our API.
How to answer
Why they ask: Very close to real FDE work. They watch how you handle bad rows and failures.
- Read with a proper CSV parser; check the header first
- Validate each row and collect errors, not crash on the first one
- Send in batches with retries and a clear report at the end
- Write one or two quick tests for the parsing
Tip: Talk through edge cases out loud: encodings, missing fields, duplicates, rate limits.
- 4Cloud, deployment and security
They wrote: “Work with platform engineers to deploy and operate AI applications within Kubernetes/OpenShift environments and integrate them into CI/CD workflows.”
How would you debug a deployment that works in staging but fails at the customer's site?
How to answer
Why they ask: Customer environments differ in ways you can't see. This tests method under pressure.
- Compare versions, config and environment variables
- Check network rules, proxies and certificates (common in enterprise)
- Look at resource limits and permissions
- Add the missing check to your install steps afterwards
Tip: List the usual suspects and how you'd check each without full access.
- 5Ownership and working with customers
They wrote: “Operate effectively in a fast-moving, ambiguous environment where technologies, security requirements, and mission priorities continue to evolve.”
Tell me about a project where the requirements kept changing. What did you do?
How to answer
Why they ask: Ambiguity is the norm. They want proof you can keep moving without a clear spec.
- The project and why requirements kept moving
- What you did to pin them down (short demos, written decisions)
- The trade-offs you made to keep shipping
- The result, with a number if you have one
Tip: Show how you reduced the change, beyond how you coped with it.
Not the one? Get the next one by email
New roles land here every day. Pick what you want to hear about.
Want the job, not just the posting? Learn how FDEs work.
FDE Info is our free weekly newsletter for forward deployed engineers: tools, field notes from real deployments, and how FDE teams hire and pay.
Free. One email a week. Unsubscribe in one click.
