Research Engineer / Scientist, Alignment Science
AnthropicSan Francisco, California, United States • Seattle, Washington, United States • New York, New York, United States
Posted April 14, 2025
280000 - 690000 USD year
Full Time
About the Company
Anthropic develops reliable, interpretable, and controllable AI systems, including Claude, an AI assistant for tasks at any scale.
Job Description
We're seeking a Research Engineer/Scientist to contribute to exploratory experimental research on AI safety, focusing on risks from powerful future systems. As a scientist and engineer, you'll design and run machine learning experiments to understand and steer the behavior of AI systems. You'll collaborate with other teams to develop techniques for keeping highly capable models helpful and honest, and ensure advanced AI systems remain safe and harmless in unfamiliar or adversarial scenarios.
Requirements
- Significant software, ML, or research engineering experience
- Some experience contributing to empirical AI research projects
- Some familiarity with technical AI safety research
Benefits
- Competitive compensation
- Benefits
- Optional equity donation matching
- Generous vacation and parental leave
- Flexible working hours
- Lovely office space