Research Scientist, Interpretability
Anthropic · San Francisco, CA
CHECKED 3H AGO
Frontier labonsite$350k–$850k
At a glance
Highlights
- Reverse-engineer how trained LLMs work to make advanced systems safe.
- Decompose models into interpretable features and circuits at scale.
- Study mechanisms behind multi-hop reasoning and planning in models.
What they offer
- Competitive compensation and benefits
- Optional equity donation matching
- Generous vacation and parental leave
- Flexible working hours
Ideal candidate
A curious experimental scientist with a strong research track record who loves collaborative team science and wants to mechanistically understand neural networks to make AI safe.
Requirements
- Strong track record of scientific research with some work on Interpretability
- Familiarity with Python
- Bachelor's degree or equivalent combination of education, training and experience
- remote policy
- Based in San Francisco office; exceptional remote work considered case-by-case
- visa sponsorship
- We sponsor visas and make every reasonable effort to get one if you receive an offer
Lab profile
About Anthropic
AI safety company building reliable, interpretable and steerable frontier AI systems.
What they build
- Claude
- Claude API
- Claude Code
Known for
- AI safety and alignment
- Model interpretability research
- Frontier LLM development
Key facts
- Founded in 2021
- Headquartered in San Francisco, California
- Backed by Amazon and Google