Software Engineer, Benchmarking

Core responsibilities:

• Run and maintain AI benchmarking infrastructure
• Integrate with AI providers and set up existing benchmarks
• Design and develop new AI benchmarks
• Facilitate internal experiments and work with the benchmarking team

This role helps evaluate frontier AI models, enabling researchers, developers, and policymakers to better understand AI development and its consequences.

Required qualifications:

• Professional level English proficiency
• Ability to overlap with UTC-8 to UTC time zones
• Ability to travel for three retreats per year
• Software engineering skills for benchmarking and infrastructure development

Benefits include:

• Fully remote work with ability to hire in many countries
• Inclusive, equitable, and supportive community environment
• Three retreats per year for team building and communication efforts
• Commitment to diversity and accessibility

Epoch AI is a research institute that investigates trends in machine learning and the economic consequences of AI, developing a comprehensive, publicly accessible knowledge base to inform policymakers, industry leaders, and society.