A complete application in a minute
Tailored resume and cover letter, ready to send.
Effectief Altruisme, a US-based organization focused on AI safety, governance, and alignment, is seeking a designer to craft evaluation tasks that test conceptual reasoning in governance, macrostrategy, and economics. The role centers on building rigorous rubrics and challenging prompts to assess model understanding.
You will develop rubrics, pinpoint hard questions where frontier models struggle, and iterate until tasks clearly distinguish strong reasoning from superficially plausible answers.
Design AI safety evaluation tasks with rubrics that measure conceptual reasoning in governance, alignment, macrostrategy, or economics. - Identify hard conceptual questions where frontier models reason poorly; create well-posed problems paired with opinionated rubrics. - Run tasks against frontier models, iterate until scores separate strong reasoning from plausible-sounding weak answers. - Requires original analysis in AI risk, alignment, macrostrategy, economics, or governance with articula…
Wie AI-modellen laat meedenken over moeilijke vragen, zoals hoe je krachtige AI veilig en bestuurbaar houdt, moet weten waar die modellen overtuigend klinken maar slecht redeneren. Jij bouwt de toetsen die dat zichtbaar maken: één goede toets meet elk volgend model opnieuw, al bepalen veiligheidsteams en beleidsmakers zelf wat ze met de uitkomsten doen.