Researcher

Key Responsibilities:

• Review benchmarks: Assess a new benchmark at least every two weeks, evaluating methodology and what a 'good performance' implies about AI capabilities.
• Publish and maintain reports: Write up public-facing reports on new benchmarks and periodically update them as new versions and models make progress.
• Dig into data: Examine individual tasks within benchmarks in detail, using coding agents while retaining critical oversight.

What we're looking for:

• You excel at written communication, with first drafts that are clear and publication-quality.
• You think critically about research methodologies and have strong opinions on benchmark design.
• You're familiar with existing AI benchmarks and have ideas for new ones.

Compensation & Benefits:

• Annual salary of $100,000–$200,000 USD, depending on location and experience.
• Fully remote environment with flexible hours, generous PTO (30 days protected, unlimited personal/sick leave), and 4 months paid parental leave.
• Comprehensive benefits including health insurance, pension, and a flexible expense policy for tools and equipment.