Research Engineer / Scientist, Alignment Science - London
Anthropic
London, United Kingdom
£260,000—£370,000 gbp py
On-site
Machine learning experiments
Ai safety research
Empirical ai research projects
Anthropic's mission is to create reliable, interpretable, and steerable AI systems that are safe and beneficial for users and society
Job Summary
Anthropic's mission is to create reliable, interpretable, and steerable AI systems that are safe and beneficial for users and society.
The Research Engineer/Scientist will contribute to exploratory experimental research on AI safety, focusing on risks from powerful future systems, often in collaboration with other teams.
The role involves building and running machine learning experiments to understand and steer AI behavior, with specific research areas including AI Control and Alignment Stress-testing.
Matching Summary
Anthropic's mission is to create reliable, interpretable, and steerable AI systems that are safe and beneficial for users and society.
Salary
£260,000—£370,000 GBP
Skills & Requirements
Must-have
Machine learning experiments
AI safety research
Empirical AI research projects
Python interviews
Collaborative projects
Nice-to-have
Helpful, honest, and harmless AI
Understanding AI alignment challenges
Advanced AI systems risks
Picking up slack
Caring about AI impacts
Key Requirements
Significant software, ML, or research engineering experience