Key skills
AIMLLarge Language ModelsCommunication
About this role
Role Overview
- Develop and lead strategy for measuring model capabilities
- Research and build evaluations for model performance
- Lead evaluation coverage across the organization
- Shape evaluation narratives for model releases
- Lead and mentor a team of researchers and engineers
- Design evaluation frameworks balancing rigor and practical demands
- Foster relationships across research teams to inform training decisions
- Contribute through publications and community engagement
Requirements
- Significant experience designing and running evaluations for large language models or similar complex ML systems
- Experience leading technical projects or teams
- Comfortable designing experiments and writing code
- Strategic thinking about what to measure and why
- Ability to synthesize information from multiple teams
- Clear communication of complex findings to varied audiences
- Results-oriented with experience in fast-paced environments
- Passion for AI safety with a desire to positively influence AI development
Benefits
- Competitive compensation
- Generous vacation and parental leave
- Flexible working hours
- Optional equity donation matching