AI agent builder internship, open worldwide
Most people are still writing prompts into a chat box. You will be building agents that run a business overnight, on real client accounts, from your first month. Open worldwide, and you can apply from anywhere.
- Location
- Fully remote
- Open to
- Worldwide
- Length
- 3 months minimum
- After that
- Job offer for the right person
Last updated 2026-09-03. This role is open until 2027-08-09.
Who we are looking for
This is for you if
We are not filtering on qualifications, and there is no minimum grade or age. What we are looking for is someone who has already made something, can talk about it honestly including the parts that went wrong, and would rather find out they were mistaken than be left thinking they were right. Every internship here works on live systems from the first fortnight, so the trait that matters most is being comfortable with real consequences and quick, direct feedback about them.
- You have already built something with AI on your own, even if it was small and even if it broke. A weekend project counts. A finished degree does not.
- You are comfortable being wrong in public. Our whole build process is one long argument with the evidence, and the person who says 'I checked, and I was wrong' is the person who gets promoted.
- You want to work on live systems rather than exercises. Everything you touch here belongs to a paying client or to us.
The work itself
What you will actually do
This is the real job, not a summary of it. Each of these lands in your first weeks rather than being held back until you have proved yourself on something artificial. You will be paired with someone senior, every job arrives with a written brief and a clear definition of done, and everything is reviewed by a human before it reaches a client. That is how we can put an intern on live work safely: the rails are strict, so the work does not have to be small.
- Write and test the instructions that decide how an agent behaves, then prove they hold by trying to break them
- Wire agents into the tools they need, a CRM, a calendar, a website, a database, so they can finish a job instead of just describing one
- Build the test rigs that catch an agent doing the wrong thing before a client ever sees it
- Read real conversations between our agents and real customers, and find the exact line where an answer went wrong
- Ship your work to a live site or a live account, then walk it yourself as if you were the customer
What you take away
What you will learn
These are the things that transfer. Tools change and frameworks come and go, but the habits below hold on any stack, at any company, for the rest of your career. They are also the things almost nobody is taught explicitly, which is why we teach them deliberately rather than hoping you absorb them.
- How an AI agent is actually built in production, which is much less about clever prompting and much more about tools, memory, and knowing when the agent should refuse
- How to verify your own work so that 'it is done' means something, which is the single hardest habit to build and the one that separates people who ship from people who demo
- How a small company runs on AI end to end, because you will see the sales, the delivery and the operations, not one slice of it
Tools you will use
- Claude and Claude Code
- Git and GitHub
- APIs and webhooks
- A real CRM with real customer data
- Playwright for testing what a human actually sees
The detail
What the job is really like
What an AI agent builder actually does all day
An AI agent is not a chatbot with a nicer personality. It is a piece of software that has been given a job, a set of tools, and the judgement to know when to use them. Our sales agent reads an enquiry, checks the calendar, answers the question that was actually asked, and books the call. Our operations agent reads the night’s work, finds what broke, and fixes it before anyone wakes up.
Building one means deciding what the agent is allowed to do, what it must never do, and how anyone will know the difference. Most of the job is not writing prompts. It is plumbing and proof. The plumbing is connecting the agent to the systems where the work really lives, the CRM, the website, the database, the calendar, because an agent that cannot read the calendar cannot book anything. The proof is the harder half, and it is where most people give up.
Why proof is the whole job
Anyone can get an AI to produce something that looks right. The skill worth hiring is being able to tell whether it is right. We have a rule here that you will hear constantly: a green test is not a fix, and a check written from the same assumption as the code can never fail.
That sounds abstract until it costs you a day. It is the difference between “the page builds” and “a person on a phone can actually read it”. Between “the API returned 200” and “the customer got their answer”. You will learn to write the check that could fail, watch it fail on a deliberately broken version, and only then trust it when it passes. That order matters more than anything else you will learn here. Most people who arrive have never been taught it, and every one of them says it is the thing that changed how they work.
The kind of person who does well here
The people who thrive are curious and slightly stubborn. They read the actual file instead of guessing what is in it. They notice when two numbers on the same screen disagree. They are happy to say “I do not know yet” and then go and find out, and they are not precious about being corrected in front of other people.
The people who struggle are the ones who want a spec handed to them in full. We will give you a clear objective, the sources to read, the boundary of what not to touch, and the shape of what done looks like. What we will not do is tell you every keystroke, because working out the middle is the part that teaches you anything. If that gap excites you, you will enjoy this a great deal. If it worries you, this is probably not the right programme, and we would rather you knew that now.
What you will build in three months
In your first fortnight you will ship something small and live. It might be a single agent skill, a test rig, or a fix to an agent that is answering a question badly. It will be real, and you will walk it yourself as the customer before anyone else sees it.
By the end of the first month you will own a piece of a working agent, with the tests that guard it. By month three, people who have done well have built an agent from a blank folder to a live deployment, including those tests and the documentation that lets someone else run it without asking you questions. That is a genuine portfolio piece and it is yours to show whether you stay with us or not. It is also, in our experience, more than most people build in a year of a junior job, because nothing here sits in a backlog waiting for approval.
Where the work comes from
We are an AI company, not an agency that bolts AI onto marketing. We build a business its whole AI team: the website, the agents that work it, the CRM, and one dashboard to run it all from. That means the agents you build have a job to do and a customer who notices when they do it badly, which is a much better teacher than any course.
We have deployed 500+ AI agents and built 300+ AI systems, and we have been building with AI since 2019. The clients range from a martial arts school to a medical device consultancy to an M&A adviser, so the problems change shape constantly and you cannot solve them by pattern matching. You will not be working on toy problems, and you will not be given a sandbox version of the work while someone senior does the real thing.
How the training actually works
You will be paired with someone senior and given jobs with a clear brief: the objective, the sources to read, what not to touch, the output we expect, and how we will know it is finished. That structure is deliberate. Vague instructions are the main reason junior work goes wrong, so we removed them.
You will get direct feedback, quickly, and it will be about the work rather than about you. We keep a written record of every mistake we have made and what it taught us, and you will read it early. It is genuinely humbling, and it is the fastest way we know to stop someone repeating a fault that has already cost us a week. You will add to it too, because you will find new ways to be wrong and that is expected rather than punished. The only thing we treat seriously is hiding it.
What we actually read
The paragraph about what broke is the part we read most closely. Anyone can show a working project. Far fewer people can describe the moment it did not work, what they assumed, and how they found out they were wrong. That is the whole job, so it is what we screen for. If your application is interesting we will send you a small practical task, and it is a problem we have already solved so we can compare your approach to ours rather than get free work out of you.
Applying
Six fields, then it is with us
No CV template, no covering letter, no application theatre. A person reads every one.
Questions people ask about the AI Agent Builder Intern role
Do I need a computer science degree to apply?
No. We look at what you have built, not what you have studied. A rough working project you can explain honestly beats a degree with nothing behind it. Send us the link and tell us what broke and how you worked it out.
How much programming do I need to know?
Enough to read code and change it without panicking. You do not need to be a strong engineer on day one, but you do need to be someone who reads the error message carefully instead of guessing and hoping.
Is this internship fully remote?
Yes, fully remote, and we accept applications from anywhere. The job listing names the countries we can currently contract through, so if you are outside them say so in your email and we will tell you honestly whether we can make it work.
How long is the internship?
A minimum of three months, and if you are good there is a job at the end of it. That is the whole point of the programme: we are training people we actually want to keep on the team.
What does a normal week look like?
You get real jobs with a written brief and a clear definition of done, not busywork. You build, you test, you show your receipts, and you get direct feedback quickly. Expect to ship something live in your first fortnight.
Will I be working on real client accounts?
Yes, under supervision. Every change is reviewed by a human before it reaches a client, and nothing goes live without someone saying yes. You learn on the real thing, safely, which is the only way this sticks.
Think you would be good at this?
We would rather see one real thing you made than a perfect CV. Send it over with a paragraph about what broke and how you worked it out.