Uma candidatura completa num minuto
Currículo e carta de apresentação personalizados, prontos a enviar.
Safety Talent Limited in San Francisco is seeking a role focused on aligning AI systems with human values and intent. You will design and implement solutions to ensure AI behaves as intended, even in complex scenarios.
You will develop alignment capabilities for subjective challenges, design evaluations to measure AI risks, and build tools to study robustness as capabilities increase. You will also create human-AI interaction methods to improve supervision and control.