Research Engineer, Interpretability
Anthropic · San Francisco, CA
CHECKED 3H AGO
Frontier labonsitesenior$315k–$560k
At a glance
Highlights
- Reverse-engineer how trained language models work to make them safer.
- Build specialized infrastructure powering interpretability research at scale.
- Bring interpretability research into production safety audits of frontier models.
What they offer
- Competitive compensation and benefits
- Optional equity donation matching
- Generous vacation and parental leave
- Flexible working hours
- Lovely office space to collaborate with colleagues
Ideal candidate
A curious, collaborative engineer with 5+ years building software who loves diving into unfamiliar systems and partnering with researchers to advance AI safety and ethics.
Requirements
- 5-10+ years of experience building software
- Highly proficient in at least one programming language and productive with Python
- Extremely curious about unfamiliar domains and able to learn quickly
- Strong ability to prioritize impactful work with ambiguity
- Prefer fast-moving collaborative projects
- Curious about interpretability research and AI safety
- Care about societal impacts and ethics of work
- Comfortable working closely with researchers
- Bachelor's degree or equivalent combination of education, training and experience
- remote policy
- Based in San Francisco office, open to exceptional remote candidates on a case-by-case basis
- visa sponsorship
- We do sponsor visas, but aren't able to successfully sponsor visas for every role and candidate
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