Research Scientist

Skills

About the Role

You will own research on frontier AI evaluation and auditing from scoping through delivery. You will design and run model evaluations, develop audit methods and protocols, build reproducible experimental pipelines, analyze results, and produce audit reports and recommendations. You will publish and present research, contribute to methodological standards, and handle confidential systems and findings carefully.

Requirements

• Track record of independent AI or machine-learning research
• Roughly three or more years beyond a PhD or equivalent, or a comparable record of delivered work
• Ability to design rigorous empirical studies and reason about measurement, uncertainty, and evidence
• Experience with large language models or modern AI systems
• Ability to develop research plans and communicate clearly in a remote environment
• Motivation to work on AI safety, AI governance, and third-party auditing full-time

Responsibilities

• Own a line of research on frontier AI evaluation and auditing
• Design and run evaluations of closed and open-weight AI systems
• Develop audit methods and evaluation protocols
• Build reproducible experimental pipelines for model testing and analysis
• Produce audit reports and actionable recommendations
• Publish and present research through papers, tools, talks, and public writing
• Contribute to research planning and methodological standards
• Handle confidential company systems, practices, and findings appropriately

Benefits

• Comprehensive medical benefits with reimbursement of eligible HRA expenses
• 6% unrestricted retirement contribution
• Unlimited PTO
• Work enablement and professional development package up to $22,200 per year

Hiring Process

Level and title are set during the interview process.