AI Engineer

The prompt is the easy part. Maybe this is your situation. You got a Claude Code or Copilot license at work this year. Everyone did. But you aren’t satisfied with simply using it to complete your tasks faster. You want to do more. You compare harnesses. You try a new model the day it is released. You build a loop of agents, then a graph of them. You put a workflow behind an endpoint, try a vector database just to see how it behaves, build a semantic index over your own notes, ship a small app nobody asked for. You want this to be your real job, but you have to take that next ticket anyway. Or maybe it is this. You are past that. You have the Max accounts and the API keys. Your AI bill is in the tens of thousands of kronor a month and you think it is cheap. You are building the foundations, pushing what an autonomous model can actually do, and you are good at it. The problem is that you are alone. Nobody at work does what you do, and when you figure something out there is no one to argue with about it. If either of these is you, keep reading. If you have been both, a year apart, we should talk today. What we do Prompting stopped being the hard part a while ago. Everyone does it now. The hard part is the step after: building the structure that lets autonomous models like Claude Fable and GPT-6 plan, build, test, deploy and ship a complete application, with no human writing code, and with code, architecture and tests of a quality no developer sustains by hand. That is TokenTek's whole job. We have migrated millions of lines of legacy code this way, fully autonomously. Independent external code reviews have given the code and architecture our structures produce their highest rating, and we will show you the reports in the first interview. Nobody here writes code by hand. When something is manual, we build the workflow that does it. The tools change with the client. The way we work does not. We have shipped apps with a millions of downloads and a banking app with a million users. Our systems run inside companies in finance, automotive and shipping. You would work forward deployed: inside the client's team, with their management, from first idea to running system. What you would do here You design the checks the model cannot game: the specification, the evals, property and differential tests, and the gates between build, deploy and release. When the model writes both the code and the tests, your job is to make sure the tests mean something.You decide what each model is for, what goes in its context and what it retrieves, and you read the traces when a run goes wrong.You run legacy migrations at the scale of millions of lines, autonomously, and you prove the result is correct.You build the data layer: retrieval, embeddings, vector search and knowledge graphs, exposed as tools and endpoints the client's systems can call, with evals that show it works.You are responsible for quality. What you ship is built to pass an external review, not just a demo.You sit with the client's team, understand the actual problem, and take it from vision to production.If you like teaching, there is room for that too. Together with Hubbau we run a twelve-month AI engineering program for M.Sc. graduates, with our engineers as coaches. What we need from you M.Sc. in computer science, systems architecture, informatics or similar.At least two or three years of building production software, preferably also with experience from data integrations or ML models. There is no upper limit.Being able to present something you built with AI where the model did the work and you built the structure. A repo, a demo, a workflow. Preferably something with real users.Opinions. You know how the models and harnesses differ, and you can argue for your choices.Judgment. Models will hand you working code all day. You know the difference between working code and good architecture, and you insist on the second.Swedish and English, spoken and written. Several of our clients require both. What you get This work, all day, on the company's account instead of your own.Colleagues who read the same release notes you do and are passionate about AI.Exciting projects where you can grow your skills in a small specialized team.Generous vacation, pension and insurance benefits, plus team trips worth closing your laptop for. Practicalities Full-time, based at our office in Göteborg. We work mostly from the office, with flexibility when you need it. How to applySend your CV and a link to the thing you built to hello@tokentek.ai, with "AI Engineer" in the subject line. We read every application ourselves.