Researcher, Interpretability

Core responsibilities:

• Perform cutting-edge research with large language and vision models to improve understanding of deep neural network features
• Plan and run interpretability experiments, analyzing the results
• Implement and maintain open source interpretability tools, such as concept erasure
• Review and synthesize academic literature relevant to the interpretability of AI systems

This role contributes to improving the understanding of AI systems through interpretability research, helping to make AI development more transparent and safer for broader adoption.

Required skills and qualifications:

• Experience with large language and vision models research
• Ability to plan and run interpretability experiments
• Proficiency in implementing and maintaining open source interpretability tools
• Strong academic literature review and synthesis skills

No specific benefits, compensation, or perks mentioned in the provided description.

EleutherAI is an organization focused on AI research, particularly in developing and understanding large language and vision models to advance the field of artificial intelligence.