Senior Research Scientist, Reward Models
Questa offerta fa per te?
Crea il mio CV Crea il tuo CV e scopri la tua percentuale di corrispondenza con questa posizione — e con tutte le altre.
Segui le tue candidature da mobile L'app gratuita Whileresume, su iPhone e Android.
La posizione
Lead cutting-edge research on reward model architectures and RLHF training for large language models.
Develop rubric-based grading and evaluation methods to improve interpretability and consistency.
Study reward hacking, specification gaming, and robust alignment strategies.
Design large-scale experiments to assess generalization, robustness, and failure modes.
Collaborate with Finetuning and Alignment Science teams to translate insights into production improvements.
Mentor researchers, publish findings, and grow institutional knowledge around reward modeling.
Develop rubric-based grading and evaluation methods to improve interpretability and consistency.
Study reward hacking, specification gaming, and robust alignment strategies.
Design large-scale experiments to assess generalization, robustness, and failure modes.
Collaborate with Finetuning and Alignment Science teams to translate insights into production improvements.
Mentor researchers, publish findings, and grow institutional knowledge around reward modeling.
Vedi l'annuncio completo
Mansioni, profilo, competenze e vantaggi — crea il tuo account gratuito.
o
Hai già un account?
AccediQueste offerte potrebbero interessarti
Nessuna offerta davvero simile per ora — ecco le più recenti.