Search
Go
AI Safety Research Fellow
GREATER LONDON · GB
—
Full-time
MID
About the Role
AIXI Labs is offering a research fellowship in AI safety. The role involves theoretical and empirical research in areas including algorithmic information theory, reinforcement learning, and LLM-based agent evaluation. The fellow will be based in London and contribute to cutting-edge AI safety research.
Responsibilities
- Conduct theoretical and empirical research on AI safety and related areas.
- Develop and evaluate AI agents based on large language models.
- Publish research findings in academic venues and collaborate with other researchers.
Requirements
- Strong background in machine learning, artificial intelligence, or a related field.
- Experience with reinforcement learning and/or large language models.
- Programming skills (e.g., Python) for research implementation.
Nice to Have
- Experience with AI safety research.
- Knowledge of algorithmic information theory.
Tech Stack
LLMReinforcement Learning
AL
AIXI Labs
Greater London · GB · 10+ employees
AIXI Labs (also known as the AI X-risk Institute) is an artificial intelligence safety organization dedicated to developing the science of superintelligent agents and addressing the existential risks they pose to humanity. It focuses on algorithmic information theory, continual reinforcement learning, and modeling AI risk factors and safety mitigations in the framework of the AIXI mathematical model.
