Research Engineer Interpretability
AI safety and research company building reliable, interpretable, and steerable AI systems, including the Claude product family and developer platform.
Maintainer signals as of 9/24/2026
Funding history
About Anthropic
Anthropic PBC develops frontier AI systems and deploys them through Claude products and the Claude Platform, with a stated focus on safety, interpretability, and steerability.
Skills
Candidate Availability
Required and preferred rules are kept separate and reflect the wording in the original posting.
About the Role
You will build and maintain specialized inference and training infrastructure, including instrumented model passes, activation extraction, and steering-vector application. You will resolve performance bottlenecks, create research tools and platforms, support production safety audits, and work across model internals, accelerators, and research tooling.
Requirements
- 5-10+ years of software development experience
- Proficiency in at least one programming language
- Productivity with Python
- Ability to learn unfamiliar technical domains quickly
- Ability to prioritize impactful work amid ambiguity
- Ability to translate research needs into engineering solutions
Responsibilities
- Build and maintain specialized inference and training infrastructure
- Implement instrumented forward and backward passes, activation extraction, and steering-vector application
- Resolve scaling and efficiency bottlenecks
- Design tools, abstractions, and platforms for research experimentation
- Bring interpretability research into production safety audits
- Work across model internals, accelerator optimization, and research tooling
Benefits
- Optional equity donation matching
- Generous vacation
- Parental leave
- Flexible working hours