Applied AI Engineer 3
Posted 4 days ago
The role in short
Lead forward-deployed engagements to architect, build, and field production AI agents and tools that automate workflows for intelligence operators.
Applied AI Engineer 3 - (Python, LLM, MCP)
Clearance: TS/SCI - Polygraph required
Position ID: 20-16-054-SWE3
Location: Columbia, Maryland
Description:
Brings AI into the operations organization, embedding engineers with the operators, analysts, and developers who carry out the CNO mission. Our engineers learn how those teams work, find the tasks that consume their time, and build AI agents and tools that let them move faster without giving up accuracy or control. We build on both frontier models and on-premises open-weight models, served through the customer's enterprise AI platform, and turn them into mission capabilities such as agents that triage incoming data, automate repetitive tradecraft, or research across disparate sources on an analyst's behalf. We are now introducing autonomous agents the mission can trust: agents that take real actions within guardrails, are measured against evaluations built with the people who use them, and log every step so a reviewer can follow what they did. As a senior Applied AI Engineer, you will lead forward-deployed work with a mission customer from the first conversation through production and set the technical direction for the agents your team builds. You will mentor engineers who are newer to applied AI and help define how our team develops software with AI, including the review standards and validation layers that let us put autonomous coding agents to work on mission code. This role suits an experienced engineer who wants to shape how AI is fielded across operations and grow into project leadership.
- Lead forward-deployed engagements with operations customers: elicit requirements from operators and analysts, identify the workflows where AI saves the most time, and deliver solutions from prototype to production.
- Architect and build agentic systems in Python that connect LLMs, MCP servers, Skills, and subagents to mission data sources and existing operational tools.
- Design guardrails for autonomous agents, including scoped permissions, human approval gates, and audit logging, so agents can act on operational systems safely.
- Build evaluation suites with mission users that measure the accuracy, reliability, and failure modes of AI capabilities, and use the results to decide when a capability is ready to field.
- Evaluate new models, frameworks, and AI design patterns, both frontier and open-weight, for fit against mission problems, and brief findings and tradeoffs to technical and government leadership.
- Use AI coding agents (e.g., Claude Code) in daily development, and help define team standards for reviewing, testing, and validating AI-generated code.
- Mentor engineers through design reviews, code reviews, and pairing, and lead technical design discussions for your project area.
- Communicate progress, risks, and tradeoffs to project leads and government stakeholders.
Position Required Skills:
- Extensive professional software engineering experience with advanced Python proficiency, including production services, APIs, and data pipelines that users depend on.
- Experience building LLM applications or agentic systems that use tool/function calling, structured outputs, context management, and multi-step workflows.
- Experience working directly with end users or mission customers to turn ambiguous operational problems into delivered software.
- Experience designing tests, evaluations, or validation layers for AI or other non-deterministic systems.
- Experience using AI coding assistants or agents (e.g., Claude Code, Codex, Copilot) for code generation, refactoring, and debugging, with the review discipline to own and explain everything they produce.
- Technical leadership experience, such as serving as tech lead, leading design decisions, or mentoring engineers.
- Experience with Git, CI/CD pipelines (GitLab preferred), Docker/Kubernetes, and Atlassian tools (Jira, Confluence).
- Strong written and verbal communication with technical and non-technical audiences.
Nice to Haves
- Experience with Model Context Protocol (MCP), Skills, subagents, or multi-agent orchestration frameworks such as PydanticAI or LangGraph.
- Experience securing LLM applications against prompt injection, data leakage, and over-permissioned tool access.
- Experience with retrieval systems (RAG, vector databases, Elasticsearch).
- Experience building spec-driven or autonomous development pipelines with AI coding agents.
- Prior forward-deployed or embedded customer-facing engineering experience.
- Experience with production CNO capabilities and operations, or knowledge of end-to-end SIGINT collection and analysis systems.
SWE3 Qualifications:
A minimum of twelve (12) years of experience as a SWE in programs and contracts of similar scope, type, and complexity is required. Bachelor's degree in Computer Science or related discipline from an accredited college or university is required. Four (4) years of additional SWE experience on projects with similar software processes may be substituted for a bachelor's degree.
Salary Range: $241k-$295k (Annually)
The range displayed above is a likely salary range for this position. This is not, however, a guarantee of compensation or salary. Rather, salary will be set based on experience, geographic location and possible contractual requirements and could fall outside of this range.
Akina is a Woman Owned, Service Disabled, Veteran Owned, Small Business, looking for talented and ambitious individuals to join our team. We offer a generous compensation package that includes 24 days PTO accrued annually and 11 federal holidays. Our 401k is 100% vested on your start date and the company makes a direct contribution worth 10% of your salary. Akina covers 100% of healthcare costs for employees and 50% toward dependents. We offer educational assistance towards college classes and will cover costs associated with job related training and certifications.
Akina is committed to excellence and creating innovative and flexible solutions for our clients. We are a small company with an open ear to our employees' needs in order to attract and retain quality talent that enables our customer's mission.
We are an equal employment opportunity employer and all qualified applicants will receive consideration for employment without regard to race, color, religion, sex, national origin, disability status, protected veteran status, or any other characteristic protected by law.
Prep for this interview
5 questions likely to come up at Akina, Inc., each matched to a line in this posting.
- 1LLMs, RAG and agents
They wrote: “Architect and build agentic systems in Python that connect LLMs, MCP servers, Skills, and subagents to mission data sources and existing operational tools.”
When would you use an agent that takes actions, and how do you keep it safe?
How to answer
Why they ask: Agent work is growing fast in FDE postings. Senior candidates are expected to know where agents fail.
- Use agents for multi-step tasks with clear success checks; avoid them where one wrong action is costly
- Give the agent narrow tools and permissions, not broad access
- Require human approval for risky actions
- Log every step so the customer can audit it
Tip: Start from the cost of a wrong action. Limit what the agent can do, and log everything.
- 2Cloud, deployment and security
They wrote: “Experience with Git, CI/CD pipelines (GitLab preferred), Docker/Kubernetes, and Atlassian tools (Jira, Confluence).”
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.
- 3Discovery and scoping
They wrote: “Lead forward-deployed engagements with operations customers: elicit requirements from operators and analysts, identify the workflows where AI saves the most time, and deliver solutions from prototype to production.”
A customer says “we want AI in our claims process.” What do you ask in the first meeting?
How to answer
Why they ask: Most FDE work starts this vague. They want to hear you find the real problem before you pick a tool.
- Map the current process: who touches a claim, in what order, with which systems
- Find the slowest or most error-prone step and ask what it costs them
- Agree on one measurable goal (for example time per claim, or error rate)
- Ask what data you can access, and who signs off on security
Tip: Ask about the work, not the technology. Who does it today, how long it takes, what a mistake costs, and how they'd know it got better.
- 4Integrations and APIs
They wrote: “Extensive professional software engineering experience with advanced Python proficiency, including production services, APIs, and data pipelines that users depend on.”
How would you set up single sign-on for a large customer?
How to answer
Why they ask: SSO (SAML or OAuth/OIDC) is a common first task in enterprise deals and a common source of delays.
- Confirm their identity provider (Okta, Entra ID, Google) and protocol
- Exchange metadata and test in a staging tenant first
- Map user groups to roles in your product
- Plan for user removal: what happens when someone leaves the company
Tip: Mention the people involved, and the protocol second. The customer's identity team usually controls the timeline.
- 5Ownership and working with customers
They wrote: “Experience working directly with end users or mission customers to turn ambiguous operational problems into delivered software.”
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.
