Tech and design
Research Scientist, Interpretability
AnthropicSan Francisco, CA
- Pay$350,000–850,000 per year
- WhereSan Francisco, CA
- Skills and toolsPython, Large language models, Mechanistic interpretability, Experimental design, Neural network reverse engineering, Feature analysis, Circuit analysis, Data visualization
- You’ll needBachelor’s degree or equivalent, Relevant field of study
- ReferenceRef. 5383
- In the paper untilThu 19 Nov
About the job
Research scientist, interpretability at Anthropic. $350,000–$850,000 a year. Hybrid, with at least 25% office time expected. Develop methods and run experiments to reverse-engineer large language models; Python required. Bachelor’s degree or equivalent and a relevant field of study.
This is our short summary. Read the full posting on boards.greenhouse.io.
Found on boards.greenhouse.io. Not placed by the employer; applications go to the original posting.