405K–485K USD / year
Staff+ Fullstack Software Engineer, Safeguards Engineering
FullstackHybrid — San Francisco, CA | New York City, NY
Published on 2026-10-09
These details were extracted automatically from the original listing. They may not be complete or fully up to date — it's worth checking the original job post.
About this role
The role involves building safety and oversight mechanisms for AI systems, focusing on monitoring model behaviors and preventing misuse. You will design internal review tools, build interfaces for human-agent supervision, and visualize abuse patterns.
About the company
Anthropic builds reliable and interpretable AI systems, including the Claude family of models, for businesses and developers. The company focuses on AI safety research and practical AI assistants for enterprise and consumer use.
Stack
TypeScriptReactPython
What you'll do
- Design and build internal review tools for abuse investigation
- Build interfaces for human supervision of agents
- Surface abuse patterns for research teams
- Own frontend architecture for sensitive data tools
What we're looking for
- Bachelor’s degree in Computer Science or equivalent experience
- Proficiency in TypeScript and React
- Comfortable working in Python
- Ability to work across the stack
- Strong communication skills
Nice to have
- 8+ years of software engineering experience
- Experience with internal tools or operator interfaces
- Experience in abuse detection and mitigation
- Experience building trust and safety detection mechanisms
Benefits
- Equity donation matching
- Generous vacation and parental leave
- Flexible working hours