Intuitive Machines
Intuitive Machines

Forward Deployment Application Engineer

Houston, TXOn-siteSeniorFull-time

Posted 11 days ago

The role in short

Embed with spacecraft engineers and business users to build, evaluate and deploy production LLM applications, connectors and agents in six-week sprints.

About Intuitive Machines:

Intuitive Machines is an innovative and cutting-edge space company making cislunar space accessible to both public and private customers. Our mission is to further science and exploration, communications, and economic progress from the Earth to the Moon and beyond. With multiple NASA lunar missions in development and additional private missions on our manifest, we pride ourselves in supporting NASA, our customers, and the nation in paving the way to return humans to the surface of the Moon. Our world-class team includes experts in all aspects of spacecraft subsystems design, development, and test, on-orbit operations, and safety.

About the Position:

Build and deploy AI applications that improve spacecraft engineering, manufacturing, and services. As a member of the AI Strike Team, you will work directly with engineers and business users to turn prioritized problems into useful software through six-week delivery sprints.

You will own application delivery from discovery and prototyping through integration, evaluation, deployment, and technical handoff. Success means measurable improvements in cycle time, engineering effort, quality, or program execution, supported by reliable applications used in real workflows.

What you will build

The initial focus is five foundations: self-service access to approved data for LLM use; connectors for users who need help accessing data; use-case-specific subsystem assistants; curated datasets requiring extraction, transformation, and loading; and flight software development tools operating within an approved GovCloud AI environment. Evolve proven workflows into bounded agents as their reliability and value justify it.

Responsibilities:

  • Embed with users to observe actual work, map handoffs and bottlenecks, establish baselines, and define a feasible MVP with the Product Lead and domain owner.
  • Build application interfaces, backend services, APIs, and workflow automation. Put working prototypes in front of users early and improve them through observed use.
  • Integrate enterprise and engineering systems through reusable connectors, APIs, and data transformations. Preserve source permissions, revisions, configuration, units, and provenance.
  • Implement retrieval-augmented generation, structured outputs, and tool calling with grounded answers, citations, and explicit human approval where needed.
  • Create representative evaluation cases and regression tests. Measure task completion, retrieval accuracy, review effort, latency, reliability, and operating cost.
  • Deploy through approved GitLab CI/CD and DevSecOps patterns. Implement monitoring, error handling, access controls, recovery, and documentation for sustainment.

Requirements:

  • Must be a US Citizen or permanent resident
  • Bachelor’s degree, four additional years of experience may be substituted for a degree
  • Minimum of 15 years of software, application, solutions, or data engineering experience, with evidence of shipping and supporting software used by real customers.
  • Strong Python and API-development skills; experience building usable application interfaces in TypeScript, JavaScript, or a comparable framework.
  • Hands-on experience delivering LLM applications, including retrieval, structured outputs, tool integration, and evaluation. Ability to distinguish model limitations from data, workflow, and software defects.
  • Experience integrating APIs, databases, documents, and enterprise systems; practical understanding of authentication, authorization, data modeling, and data quality.
  • Proficiency with Git, automated testing, CI/CD, containers, and cloud deployment. Ability to debug across application, integration, and infrastructure boundaries.
  • Ability to lead technical discovery, explain tradeoffs clearly, work through incomplete requirements, and deliver a bounded solution within a short sprint.
  • Sound judgment in handling sensitive information, maintaining traceability, and designing workflows with accountable human review.

Preferred Experience

  • Aerospace, defense, manufacturing, or another regulated engineering environment; familiarity with configuration control, quality processes, and engineering verification.
  • AWS GovCloud and Bedrock, enterprise model gateways, Open WebUI, MCP interfaces, and secure development practices for CUI and ITAR workloads.
  • Integrations with PLM, ERP, MES, or ALM systems such as Teamcenter, IFS, Solumina, Jama, or GitLab; exposure to Nastran or other engineering analysis tools.

How you will work with the team

The Product Lead sets priorities and business outcomes, with AI Council oversight. You provide feasibility estimates and own application implementation. The Core Platform and DevSecOps team supplies approved infrastructure and shared services. Domain engineers validate technical outputs and retain approval authority. The AI Enablement Manager scales training and adoption; you provide demonstrations, technical guidance, and usage instrumentation.

What success looks like

  • Within 30 days, understand a priority workflow, establish its baseline, confirm data and environment readiness, and demonstrate a useful prototype.
  • By the end of the first six-week sprint, deliver an evaluated pilot to the intended users, document results and limitations, and support a scale, iterate, or stop decision.
  • Within 90 days, move a successful pilot toward supported production, demonstrate measured improvement including human review effort, and contribute reusable components for subsequent sprints.

US EEO Statement:

Intuitive Machines is an Equal Opportunity employer. All qualified applicants will receive consideration for employment without regard to sex, gender identity, sexual orientation, race, color, religion, national origin, disability, protected veteran status, age, or any other characteristic protected by law.

Prep for this interview

5 questions likely to come up at Intuitive Machines, each matched to a line in this posting.

  1. 1Discovery and scoping
    They wrote: “Ability to lead technical discovery, explain tradeoffs clearly, work through incomplete requirements, and deliver a bounded solution within a short sprint.”

    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.

    1. Map the current process: who touches a claim, in what order, with which systems
    2. Find the slowest or most error-prone step and ask what it costs them
    3. Agree on one measurable goal (for example time per claim, or error rate)
    4. 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.

  2. 2Coding
    They wrote: “Strong Python and API-development skills; experience building usable application interfaces in TypeScript, JavaScript, or a comparable framework.”

    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.

    1. Read with a proper CSV parser; check the header first
    2. Validate each row and collect errors, not crash on the first one
    3. Send in batches with retries and a clear report at the end
    4. Write one or two quick tests for the parsing

    Tip: Talk through edge cases out loud: encodings, missing fields, duplicates, rate limits.

  3. 3Integrations and APIs
    They wrote: “Build application interfaces, backend services, APIs, and workflow automation. Put working prototypes in front of users early and improve them through observed use.”

    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.

    1. Find who owns the system and get read access to a test environment
    2. Watch real traffic or logs to learn the data shapes
    3. Build a thin adapter with logging around every call
    4. 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.

  4. 4Data and SQL
    They wrote: “Experience integrating APIs, databases, documents, and enterprise systems; practical understanding of authentication, authorization, data modeling, and data quality.”

    The customer's data is spread across five systems that disagree. How do you get one clean view?

    How to answer

    Why they ask: Real deployments rarely have one source of truth. They want a practical approach, not a perfect one.

    1. List each system and what it's the best source for
    2. Pick matching keys and decide how to handle records that don't match
    3. Load into one place with clear rules, and keep the raw copies
    4. Show the customer the mismatches; they often fix the source

    Tip: Name the system the business trusts most for each field, and get the customer to agree.

  5. 5LLMs, RAG and agents
    They wrote: “Hands-on experience delivering LLM applications, including retrieval, structured outputs, tool integration, and evaluation. Ability to distinguish model limitations from data, workflow, and software defects.”

    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.

    1. Collect and clean the documents; handle permissions per user
    2. Split them into chunks, embed, and store with source links
    3. Retrieve, then answer with citations; say “I don't know” when retrieval is weak
    4. 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.

Not the one? Get the next one by email

New roles land here every day. Pick what you want to hear about.

FDE Info

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.

Similar roles at other companies

Intuitive Machines

On-site

Apply