Staff+ Fullstack Software Engineer, Safeguards Engineering

Anthropic•San Francisco, NY

5d•Hybrid

About The Position

Anthropic's mission is to create reliable, interpretable, and steerable AI systems. We want AI to be safe and beneficial for our users and for society as a whole. Our team is a quickly growing group of committed researchers, engineers, policy experts, and business leaders working together to build beneficial AI systems. This job post is for Fullstack Software Engineers only. We are looking for fullstack software engineers to help build safety and oversight mechanisms for our AI systems. As a software engineer on the Safeguards team, you will work to monitor models, prevent misuse, and ensure user well-being. This role will focus on building systems to detect unwanted model behaviors and prevent disallowed use of models. You will apply your technical skills to uphold our principles of safety, transparency, and oversight while enforcing our terms of service and acceptable use policies. 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. This flexible approach allows us to match talented engineers where they'll have the greatest impact and growth potential.

Requirements

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

Nice To Haves

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

Responsibilities

Design and build the 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 the interfaces where humans supervise agents: streaming output, interruption and approval flows, and clear provenance for every action an agent takes.
Surface abuse patterns to our research teams through the visualizations and exploration tools that make emerging patterns legible.
Own the 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.