CritPt is a public benchmark of research-level physics challenges, built to test whether frontier AI models can carry out genuine physics research reasoning rather than textbook problem solving. The benchmark paper is arXiv:2509.26574 and we recommend reading it before applying. It will tell you quickly whether this work interests you.
CritPt is a public benchmark of research-level physics challenges, built to test whether frontier AI models can carry out genuine physics research reasoning rather than textbook problem solving. The benchmark paper is arXiv:2509.26574 and we recommend reading it before applying. It will tell you quickly whether this work interests you.
We’re looking for experienced HR professionals who are native or fluent in German to help train and evaluate AI agents on realistic professional tasks. You’ll build workspaces and files, write prompts, and create grading rubrics based on real human resources work as it’s done in Germany. Experience in HR (business partnering, employee relations, compensation or talent).
We’re looking for experienced scientists and engineers who are native or fluent in German to help train and evaluate AI agents on realistic professional tasks. You’ll build workspaces and files, write prompts, and create grading rubrics based on real stem work as it’s done in Germany. Experience as a scientist or engineer in research or industry (master’s or PhD a plus).
We’re looking for experienced physicians who are native or fluent in German to help train and evaluate AI agents on realistic professional tasks. You’ll build workspaces and files, write prompts, and create grading rubrics based on real medicine work as it’s done in Germany. Experience in clinical practice.
We’re looking for experienced management and strategy consultants who are native or fluent in German to help train and evaluate AI agents on realistic professional tasks. You’ll build workspaces and files, write prompts, and create grading rubrics based on real consulting work as it’s done in Germany. Experience in management or strategy consulting.
We’re looking for experienced lawyers who are native or fluent in German to help train and evaluate AI agents on realistic professional tasks. You’ll build workspaces and files, write prompts, and create grading rubrics based on real law work as it’s done in Germany. Experience in legal practice.
We’re looking for experienced management and strategy consultants who are native or fluent in Spanish to help train and evaluate AI agents on realistic professional tasks. You’ll build workspaces and files, write prompts, and create grading rubrics based on real consulting work as it’s done in Spain. Experience in management or strategy consulting.
Help make the next generation of AI-narrated audiobooks sound genuinely human. We’re building a team of native Italian speakers who love audiobooks to help evaluate AI-narrated (text-to-speech) audiobooks in Italian (Italy). You’ll listen the way a real audiobook fan does — but with a careful, analytical ear — and flag the moments where the narration slips, so the underlying models can be made better.
Help make the next generation of AI-narrated audiobooks sound genuinely human. We’re building a team of native Dutch speakers who love audiobooks to help evaluate AI-narrated (text-to-speech) audiobooks in Dutch (Netherlands). You’ll listen the way a real audiobook fan does — but with a careful, analytical ear — and flag the moments where the narration slips, so the underlying models can be made better.