Careers
We're small, and the problems are the good kind.
Distributed systems, retrieval quality, and a habit of publishing results that do not flatter us.
Open roles
Nothing posted right now.
Which is not the same as not hiring. If you read the guides and had opinions about them, that is a better introduction than a cover letter.
What it's like
Four things that are true.
The interesting problems are not the model calls
Entity resolution that holds under concurrent writers. Provenance bookkeeping that retracts a fact only when its last supporter drops. An ontology change that is reversible. Orchestration that does not silently lose a document. The language-model part is the easy part.
Measurement over intuition
Ranking changes here get decided by measurement against labelled questions, not by whichever one sounds most reasonable in a meeting — and the intuitive answer loses often enough that this is worth the trouble. It also means being wrong internally on a regular basis and saying so.
We publish the unflattering result
The marketing site says, on the product pages themselves, that the knowledge graph has not been shown to improve answer accuracy over plain retrieval on the question sets we can score. Not buried in a doc — next to the thing we are selling. If that sounds uncomfortable rather than appealing, this is probably not the right team.
Architecture rules are enforced, not reviewed
A custom lint plugin gates the contract-first structure in CI, with no suppressions permitted. Fewer arguments in code review, and the constraint is the same for everyone including whoever wrote it.