Anthropic · San Francisco, CA · Onsite · Nov 2025
Reverse-engineer how trained LLMs work to make advanced systems safe.
$350k–$850k
Interpretability ResearchersResearch · RSC
Interpretability Researchers
Reveal how models reason internally.
- Probe activations and circuits
- Build interpretability tooling
- Share insights guiding safety
3 open3 of 3 list compensation: $315k–$850k
3 open roles
Anthropic · San Francisco, CA · Onsite · Nov 2025
Reverse-engineer how trained language models work to make them safer.
$315k–$560k
Interpretability ResearchersAnthropic · San Francisco, CA · Onsite · Nov 2025
Reverse-engineer how large language models work internally for AI safety.
$350k–$500k
Interpretability Researchers