Senior Evaluation Engineer
Design the metrics and graded datasets that tell banks whether their agents are safe to ship.
Team
Research
Location
London, UK
Type
Full-time
The role
Design the metrics and graded datasets that tell banks whether their agents are safe to ship.
You will work in a small team with direct access to customers in banking, insurance and health, and ship to production every week.
What you’ll do
Own a meaningful part of the platform end to end, from design doc to on-call.
Turn messy, real-world failures into measurable, repeatable checks.
Write and review code, metrics and docs that auditors will one day read.
What we look for
Several years building production systems, and the judgement to know when a number is lying.
Care for the people on the other side of the agent: the customer who just wants a straight answer.