Senior Research Scientist, Reward Models
Is deze vacature iets voor u?
Mijn cv maken Maak uw cv en ontdek uw matchpercentage met deze functie — en met alle andere.
De functie
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.
Bekijk de volledige vacature
Taken, profiel, vaardigheden en voordelen — maak gratis een account aan.
of
Al een account?
InloggenVergelijkbare vacatures
Andere functies die kunnen passen.