Staff+ Fullstack Software Engineer, Safeguards Engineering

Anthropic's mission is to create reliable, interpretable, and steerable AI systems.

We have multiple teams that are currently hiring within Safeguards. Team placement occurs after the interview process, taking into account your interests and experience alongside organizational needs.

Responsibilities:

• Design and build internal review tools analysts use to investigate abuse , dashboards, case queues, and evidence viewers that make high-volume, high-stakes decisions fast and accurate.
• Build interfaces where humans supervise agents: streaming output, interruption and approval flows, and clear provenance for every action an agent takes.
• Surface abuse patterns to research teams through visualizations and exploration tools that make emerging patterns legible.
• Own frontend architecture for tools handling sensitive data at scale , performance under large datasets, correctness under real-time updates, and access controls enforced end to end.

You may be a good fit if you have:

• A Bachelor’s degree in Computer Science, Software Engineering or comparable experience
• Proficiency in TypeScript and modern React; comfortable in Python for backend work
• Ability to work across the stack
• Strong communication skills and ability to explain complex technical concepts to non-technical stakeholders

Strong candidates may also:

• 8+ years of experience in software engineering position, not including internships or co-ops
• Experience building data-dense internal tools or operator interfaces, not just marketing or consumer surfaces
• Experience with integrity, spam, fraud, or abuse detection and mitigation
• Experience building trust and safety detection mechanisms and intervention for AI/ML systems
• Experience with prompt engineering, jailbreak attacks, and other adversarial inputs
• Worked closely with operational teams to build custom internal tooling

The annual compensation range for this role is $405,000-$485,000 USD.