Applied Safety Research Engineer, Safeguards
¿Es esta oferta para usted?
Crear mi CV Cree su CV y descubra su porcentaje de coincidencia con este puesto — y con todos los demás.
El puesto
Design and run experiments to improve evaluation quality, including methods to generate representative test data, simulate realistic user behavior, and validate grading accuracy.
Research how factors such as multi-turn conversations, tools, long context, and user diversity impact model safety behavior.
Analyze evaluation coverage to identify gaps and determine where better measurement is needed.
Productionize successful research into evaluation pipelines that run during model training, launch, and beyond.
Collaborate with Policy and Enforcement to translate real-world harm patterns into measurable evaluations.
Build tooling that enables policy experts to create and iterate on evaluations, and surface findings to drive upstream model improvements.
Research how factors such as multi-turn conversations, tools, long context, and user diversity impact model safety behavior.
Analyze evaluation coverage to identify gaps and determine where better measurement is needed.
Productionize successful research into evaluation pipelines that run during model training, launch, and beyond.
Collaborate with Policy and Enforcement to translate real-world harm patterns into measurable evaluations.
Build tooling that enables policy experts to create and iterate on evaluations, and surface findings to drive upstream model improvements.
Ver la oferta completa
Funciones, perfil, competencias y ventajas — crea tu cuenta gratis.
o
¿Ya tiene una cuenta?
Iniciar sesiónOfertas similares
Otros puestos que podrían encajar.