Research Lead, Evaluations and Benchmarks

• In this role, you'll ship benchmarks every 2-3 weeks measuring frontier AI safety risks and harms.
• Own the quality bar by reviewing evaluations for novelty, clarity, and reproducibility across labs.
• Manage the release process by directing freelancers and keeping researchers on schedule.
• Set the quarterly roadmap with the CTO and research leads based on emerging needs.
• Stay current with the AI safety ecosystem by reading research, maintaining lab contacts, and attending conferences.

• In this role, you'll ship benchmarks every 2-3 weeks measuring frontier AI safety risks and harms.
• Own the quality bar by reviewing evaluations for novelty, clarity, and reproducibility across labs.
• Manage the release process by directing freelancers and keeping researchers on schedule.
• Set the quarterly roadmap with the CTO and research leads based on emerging needs.
• Stay current with the AI safety ecosystem by reading research, maintaining lab contacts, and attending conferences.

Alice is a trust, safety, and security AI company.