AI SafetyFull-timeHybridFEATURED
AI Safety Researcher
Anthropic
San Francisco, CA / London
$200K – $380K
Posted 7d ago
Anthropic's safety team is hiring researchers to develop techniques for making advanced AI systems safe and aligned. Work on mechanistic interpretability, adversarial robustness, scalable oversight, and alignment techniques. This is one of the most important technical challenges of our time.
Apply for this Job →✅ Requirements
- • PhD or equivalent experience in CS, ML, or related field
- • Strong ML research background
- • Interest in AI safety and alignment
- • Excellent Python and ML framework skills
🌟 Nice to Have
- • Published AI safety research
- • Experience with transformer interpretability
- • Familiarity with constitutional AI approaches
📋 Quick Info
Company: Anthropic
Location: San Francisco, CA / London
Type: Full-time
Remote: Hybrid
Salary: $200K – $380K
Category: AI Safety
Advertisement