Research Scientist/Engineer, AI Scheming
Apollo ResearchLondon, UK / San Francisco, CA
AI safety & policy
Full-time
AI safety & policy
Full-time
Salary
USD 245,000 - USD 590,000
Routes to impact
Direct high impact on an important cause
Description
Research AI scheming through experiments on RL-trained LLMs, model organisms, evaluation techniques, and scaling laws for deceptive or reward-seeking behavior.
- Study RL dynamics behind reward-seeking, evaluation awareness, and misaligned preferences
- Design and train model organisms, then scale insights to frontier systems
- Build empirical foundations for “scaling laws of scheming”
- Develop evaluation techniques that can scale to highly evaluation-aware models
- Visa sponsorship available in the UK and US
This text was generated by AI. If you notice any inconsistencies, please let us know using this form.
