Research Engineer, Safeguards Labs

Anthropic is hiring Research Engineers to join their Safeguards Labs team. The team investigates novel safety methods for protecting AI systems and human users. The role involves scoping research projects, running experiments, and deciding when to hand off ideas to production teams. The team is small and allows for substantial latitude and high leverage.

Requirements

• Lead and contribute to research projects investigating new methods for detecting misuse of Claude
• Design and run offline analyses over model usage data to surface abuse patterns
• Develop and iterate on prototypes that could eventually feed signals into the real-time safeguards path
• Build evaluations and methodologies for measuring whether safeguards actually work
• Write up findings clearly so they inform decisions across Trust & Safety, research, and product teams

Benefits

• Competitive compensation
• Optional equity donation matching
• Generous vacation and parental leave
• Flexible working hours
• Lovely office space