✨ About The Role
- The role involves building evaluations of frontier AI models to assess identified risks and designing infrastructure to support these evaluations
- Collaborating with other teams to incorporate monitoring of real-world misuse risks into evaluation processes
- Creating full-stack applications to demonstrate evaluation results to external audiences
- Working on capability assessment, evaluations, and internal red teaming for frontier models to ensure safety of highly-capable AI systems
âš¡ Requirements
- Experienced software engineer with a track record of pushing boundaries in frontier AI models and building scalable infrastructure
- Ability to work effectively in a fast-paced research environment and deliver projects end-to-end
- Strong understanding of societal aspects of AI deployment and willingness to work cross-functionally
- Excellent communication skills and a humble attitude with a desire to contribute to team success