Belay Technologies
Belay Technologies2 open roles

Junior Software Engineer (Applied AI, Forward Deployed)

$70–190kFort Meade, MDOn-siteEntryFull-time

Posted 3 days ago

The role in short

Embed with intelligence operators to build and test agentic AI solutions, MCP servers, and data tools using Python and LLMs.

Belay Technologies provides leading-edge technology and engineering services to the DoD, as well as state-of-the-art commercial products. We are a certified Service-Disabled Veteran-Owned Small Business (SDVOSB) in the Baltimore-Washington Area. We take the smartest approach, delivering innovative solutions to our customers. Put your vision into action with Team Belay!

Junior Software Engineer

Belay Technologies has been voted Baltimore Business Journal's (BBJ) Best Places to Work 2026!

Belay Technologies is seeking a Software Engineer to join our intel team. AIMASSIST 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 an Applied AI Engineer, you will join a forward-deployed team that works directly with a mission customer, building and improving the agents, Skills, and tools they use every day. You will work under the guidance of senior engineers, learn CNO tradecraft from the operators and analysts you support, and see the results of your work firsthand. This role suits an engineer with a solid software foundation who wants to grow quickly in applied AI.

Responsibilities:

  • Develop and test components of agentic AI solutions in Python, including MCP servers, Skills, and integrations with mission data sources and tools
  • Participate in requirements discussions with operators and analysts, and learn their workflows and tradecraft
  • Build scripts and tools that convert, normalize, and extract information from customer data
  • Write test cases and evaluation examples that check whether AI capabilities return correct and reliable results
  • Use AI coding agents in daily development, and understand and review generated code before committing it
  • Collaborate with other engineers to test workflows, identify issues, and recommend fixes
  • Create documentation and user guides that help mission users adopt new AI tools

Candidates should have the following qualifications:

  • TS/SCI Clearance with polygraph
  • 3 yrs., B.S. in a technical discipline or 4 additional yrs. in place of B.S.

Candidates are required to have the following skills:

  • Proficiency in Python, including working with JSON, REST APIs, and data manipulation
  • Understanding of software engineering fundamentals, including version control (Git), testing, and debugging
  • Familiarity with LLM concepts such as prompt engineering, structured outputs, and tool/function calling
  • Experience using AI coding assistants (e.g., Claude Code, Copilot) to write, debug, or test code
  • Familiarity with Linux environments and the command line
  • Strong communication skills and willingness to learn from senior engineers and mission subject matter experts

Candidates are desired to have the following skills:

  • Experience building agentic workflows, MCP servers, or Skills
  • Experience with Docker, Kubernetes, or GitLab CI/CD
  • Experience with retrieval systems (RAG, vector databases, Elasticsearch)
  • Experience building web interfaces with React or TypeScript
  • Background in cybersecurity, or knowledge of CNO operations and SIGINT collection and analysis systems

Perks and Benefits:

  • 8 weeks paid leave - 4 weeks of personal leave, 3 Yay! days, take off on your birthday, 11 paid holidays and optional leave up to 6 days through Belay's volunteer program
  • 10% matching in 401(k) contributions vested on day one
  • $5,000 annual training/tuition
  • Student Loan Repayment Program
  • 100% company-funded HSA
  • Rich medical coverage (100% coinsurance)
  • Dental coverage including orthodontia
  • Up to $420,000 in life insurance, premiums 100% company funded
  • Amazon Prime, gym reimbursement, monthly lunches, games and prizes
  • Pet adoption program, generous referral bonus program, fun events, and more!

At Belay, we are committed to creating an environment where you can thrive both professionally and personally. We believe in transparency and fairness in compensation. Several factors influence final salary including, but not limited to, geographic location, Federal Government contract labor categories and contract wage rates, relevant prior work experience, education, specific skills and competencies and certifications. Belay offers a competitive total compensation package that includes benefits and perks, a flexible work-life balance, and career development.

Salary Range: $70,000 to $190,000

Belay Technologies is a certified Service-Disabled Veteran-Owned Small Business located in Columbia, Maryland (Baltimore/Washington area). Belay Technologies specializes in systems automation and full stack development. Belay Technologies provides leading technology and engineering solutions to the DoD, as well as state-of-the-art commercial products. We hire software engineers, web designers, test engineers, systems engineers, systems administrators, database engineers and other tech services. We are an Equal Opportunity Employer. Employment decisions are made without regard to race, color, religion, national origin, gender, sexual orientation, gender identity, age, physical or mental disability, genetic factors, military/veteran status or other characteristics protected by law.

Prep for this interview

4 questions likely to come up at Belay Technologies, each matched to a line in this posting.

  1. 1LLMs, RAG and agents
    They wrote: “Familiarity with LLM concepts such as prompt engineering, structured outputs, and tool/function calling”

    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.

  2. 2Cloud, deployment and security
    They wrote: “Experience with Docker, Kubernetes, or GitLab CI/CD”

    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.

    1. Compare versions, config and environment variables
    2. Check network rules, proxies and certificates (common in enterprise)
    3. Look at resource limits and permissions
    4. Add the missing check to your install steps afterwards

    Tip: List the usual suspects and how you'd check each without full access.

  3. 3Integrations and APIs
    They wrote: “Develop and test components of agentic AI solutions in Python, including MCP servers, Skills, and integrations with mission data sources and tools”

    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. 4Coding
    They wrote: “Proficiency in Python, including working with JSON, REST APIs, and data manipulation”

    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.

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.

More at Belay Technologies

Similar roles at other companies

Belay Technologies

$70–190k · On-site

Apply