[ research ]
Research Scientist, Interpretability
Anthropic- Location
- San Francisco, California
- Work mode
- Remote
- Type
- full time
- Listed
Applications go directly to Anthropic. Ramai takes no fee for placement and no money for ranking.
[ About this role ]
Research Scientist, Interpretability at Anthropic focused on mechanistic interpretability to understand how neural network parameters map to meaningful algorithms. The role involves reverse-engineering trained models to ensure advanced AI systems are safe and beneficial.
Skills and focus areas
- interpretability
- mechanistic interpretability
- neural networks
- reverse engineering
- ai safety
Summary written by Ramai from the original posting. Full details and requirements are on Anthropic’s careers page.
[ More at Anthropic ]
See all 675 open roles at Anthropic →[ Similar roles at other startups ]
- Protein Scientist (ph.d. Required)Epinoma
- Principal Scientist (pd/msat)Mytos
- General InterestPostEra
- Lab Technician- Quality ControlVolta Labs, Inc.
- Ai Researcherarnata
- Research Engineer - Ai SystemsYotta
[ Not quite right? ]
Tell the assistant what you’re after — stage, location, stack, visa sponsorship — and it searches every open role for you. A few questions are free, no account needed.