Research Engineer, Ai Safety & Alignment

Research Engineer at Character AI focused on AI safety and alignment. This role involves developing and implementing novel evaluation methodologies, researching cutting-edge techniques for model alignment, value learning, and interpretability, and conducting adversarial testing to ensure AI models behave in accordance with human values and intentions.

Skills and focus areas

• ai safety
• ai alignment
• large language models
• evaluation methodologies
• model alignment
• value learning
• interpretability
• adversarial testing
• bias mitigation
• toxicity mitigation
• reinforcement learning from human feedback (rlhf)
• fine-tuning