Tech Stack

Description

You will contribute to the Scientist AI agenda by clarifying key safety research questions, proposing solutions, designing ML experiments, and analyzing how the agenda fits into broader AI risk mitigation. Your work will help build safe, non-agentic AI systems.

Requirements

• PhD in relevant field or equivalent exceptional ability
• Research experience in technical AI safety, especially AGI safety
• Experience designing and running ML experiments
• Proficiency with PyTorch or Tensorflow
• Excitement to shape the Scientist AI agenda

Responsibilities

• Clarify central AI safety research questions for the Scientist AI agenda
• Analyze proposed solutions and develop novel ideas
• Design and implement novel ML algorithms and experiments for AI safety
• Scrutinize the Scientist AI agenda and prioritize experiments
• Discuss complex findings with team members from diverse backgrounds