boardintelligence - Software Engineer - AI Evaluation

• Design and build our AI evaluation suite, the systems we use to measure and improve the quality of AI output • Build across the full stack yourself, from data pipelines and backend services to the front-end tools our experts use • Work closely with prompt engineers and subject matter experts, turning their knowledge into tests, metrics and tooling • Help define how we measure AI quality, in a field where practices are still forming • Make evaluation processes and results automated as part of our SDLC, so product teams can ship with confidence • Over time, contribute to building our AI-powered products • ## Person Specification • We are looking for a strong all-round engineer who is comfortable working independently, enjoys ambiguity and wants to work at the forefront of AI quality. • Fluent written and spoken English • After three months: the first version of the evaluation suite is running and our engineering teams are using it • After six months: evaluations cover all of our AI products and are integrated into the SDLC • After twelve months: evaluation is a standard part of how we ship AI, and you are a trusted voice on AI quality across engineering • Our values aren’t just words on a wall. They capture our culture, and the behaviours we see and strive for every day. • Kindness & caring — We celebrate brilliance that comes without big egos or sharp elbows, and we win while raising each other up. • Curiosity & innovation — Entrepreneurship is in our blood. We’re inquisitive, challenge convention, think big, and move fast. • Remarkable quality & service — We take joy from delighting our clients and pride ourselves on ensuring every interaction is exceptional.