Staff+ Fullstack Software Engineer (Safeguards Engineering)

Join Anthropic, a leading AI safety and research company, as a Staff+ Fullstack Software Engineer. In this role, you will work on building safety and oversight mechanisms for AI systems, focusing on detecting unwanted model behaviors and preventing disallowed use of models. You will design and build internal review tools, interfaces for human supervision of agents, and visualization tools for surfacing abuse patterns. This position offers comprehensive benefits, a competitive salary, and the opportunity to work on impactful projects in AI safety.

Responsibilities

• Concevoir et construire des outils internes pour les analystes afin d'enquêter sur les abus, y compris des tableaux de bord et des files d'attente de cas.
• Construire des interfaces où les humains supervisent les agents, y compris le flux de sortie en continu et les flux d'interruption et d'approbation.
• Surveiller les modèles, prévenir les abus et garantir le bien-être des utilisateurs en construisant des systèmes pour détecter les comportements indésirables.
• The ability to work across the stack

Requirements

• A Bachelor’s degree in Computer Science, Software Engineering or comparable experience
• Strong communication skills and ability to explain complex technical concepts to non-technical stakeholders
• Proficiency in TypeScript and modern React; comfortable in Python for backend work
• Minimum education: Bachelor’s degree or an equivalent combination of education, training, and/or experience
• Required field of study: A field relevant to the role as demonstrated through coursework, training, or professional experience
• Minimum years of experience: Years of experience required will correlate with the internal job level requirements for the position
• We encourage you to apply even if you do not believe you meet every single qualification
• Have experience with prompt engineering, jailbreak attacks, and other adversarial inputs
• Have worked closely with operational teams to build custom internal tooling
• Have experience building trust and safety detection mechanisms and intervention for AI/ML systems
• Have experience with integrity, spam, fraud, or abuse detection and mitigation
• Have experience building data-dense internal tools or operator interfaces, not just marketing or consumer surfaces
• 8+ years of experience in a software engineering position, not including internships or co-ops

Pay

USD 405,000 - 485,000