Staff ML Engineer

Push a one-line fix. Then watch CI grind through forty minutes of tests, ninety-five percent of which never had a chance of touching what you changed. You already know the handful that mattered. The test suite doesn't — so it runs everything, every time, just in case.

That "just in case" is the most expensive habit in software delivery. Every engineering team pays it, because the alternative — knowing which tests actually matter for a given change — has been too hard to get right.

We're building the team that gets it right. This role sits at the centre of it.

🔧 The problem worth solving

Test Engine already ingests billions of test runs. We can see the tests, the code underneath them, and how the two move together — at a scale very few people ever get to work with. The raw material for the answer is already here. Nobody's turned it into predictions yet.

That's the step to take: for a given change, work out the slice of tests most likely to fail, and run only those. Get it right and teams stop re-running what hasn't changed, and spend that time where it counts — like fixing the two percent of tests most likely to break.

It's a genuinely difficult ML problem — sparse signal, cold-start on new repos, generalising across languages and frameworks, and latency tight enough to sit in the critical path. It's also close to a blank page. There's no ML org above you setting the direction — you'd set it. And not alone: we've just hired another ML engineer, so there's someone to think out loud with from day one.

🚀 What you'll own

Machine learning in Test Engine, end-to-end — the strategy, the architecture, and the models running in production.

…