Research Assistant

Core responsibilities:

• Assist with research on training and evaluating language models for AI safety
• Conduct experiments using Python libraries such as PyTorch to train and evaluate language models
• Participate in conceptual discussions about how to model desirable behavior and incentives for AI
• Analyze experimental results and support writing research papers

This role contributes to AI safety research by helping develop methods to train and evaluate language models with desirable behaviors, potentially reducing risks from advanced AI systems.

Required skills and qualifications:

• Experience with Python programming and PyTorch library
• Research skills including experimental design and data analysis
• Ability to participate in conceptual discussions about AI behavior modeling
• Academic writing skills for research paper support

No benefits information provided in the job description.

Principled Agents appears to be an organization focused on AI safety research, specifically working on training and evaluating language models with desirable behaviors and incentives.