Research Engineer / Scientist, Alignment Science
Research Engineer / Scientist, Alignment Science
Research Engineer / Scientist, Alignment Science
Anthropic
The Research Engineer / Scientist in Alignment Science at Anthropic focuses on building and running machine learning experiments to enhance AI safety and interpretability. The role involves collaborative exploratory research on AI systems, aiming to ensure they remain helpful, honest, and harmless, particularly as they approach human-level capabilities.
Qualification
- Strong background in machine learning and AI
- Experience with experimental research methodologies
- Ability to work collaboratively in a team environment
- Interest in AI safety and alignment challenges
- Familiarity with advanced AI systems and their risks
Responsibility
- Build and run machine learning experiments to understand AI behavior
- Contribute to exploratory research on AI safety
- Collaborate with teams on interpretability and fine-tuning
- Develop techniques for scalable oversight of AI systems
- Create methods to ensure AI control in adversarial scenarios
