TolokaAI is building a dataset to evaluate AI coding agents by creating realistic developer tasks and an olympiad-style evaluation framework.
Si sus habilidades, experiencia y cualificaciones coinciden con las de esta descripción del puesto, no demore su solicitud.
You will design tasks, scripts, and criteria to assess agent performance within isolated development environments and real-world codebases.
Join a remote-first, globally distributed team working on cutting-edge AI evaluation methods for top tech and research partners. xqbhyrx
#J-18808-LjbffrBy continuing you agree to our Terms & Privacy Policy.