Research Engineer, Production Model Post-training

Research Engineer on the Post-Training team at Anthropic. This role involves training production models through post-training processes like Constitutional AI and RLHF to enhance capabilities, alignment, and safety. Responsibilities include implementing and optimizing techniques, developing pipelines, and debugging complex issues.

Skills and focus areas

• constitutional ai
• rlhf
• alignment methodologies
• model fine-tuning
• model evaluation
• pipeline development
• debugging
• python
• handling multiple priorities