Staff Software Engineer, AI Safety & Safeguards

Anthropic; York and North Yorkshire; Presencial; GBP 110 000 - 160 000; Tempo integral

Vantagens oferecidas por esta oferta de emprego

Comprehensive health insurance

Fertility benefits via Carrot Fertilty

Paid parental leave 22 weeks

Flexible paid time off

Resumo da oferta

Anthropic in the United Kingdom is seeking a software engineer for the Safeguards team to build safety and oversight mechanisms for AI systems. You will monitor models, prevent misuse, and surface abuse patterns to researchers and analysts for action.

Responsibilities include building scalable detection systems, real-time defenses, and internal tooling, with a focus on safety, transparency, and policy enforcement across the stack. Premier compensation and relocation support are offered.

Qualificações

• Bachelor’s degree in Computer Science, Software Engineering or comparable experience.
• 8+ years of experience in a software engineering position.
• Proficiency in Python and TypeScript.
• Experience with integrity, spam, fraud, or abuse detection and mitigation.
• Experience with prompt engineering, jailbreak attacks, and other adversarial inputs.
• Ability to work across the stack and with cross-functional teams.
• Experience building trust and safety detection mechanisms and interventions for AI/ML systems.
• Experience with operational teams to build custom internal tooling.

Responsabilidades

• Develop monitoring systems to detect unwanted model behaviors and prevent disallowed use of models.
• Build monitoring and detection mechanisms for API partners, surfacing results for analyst review.
• Create scalable defenses and infra to improve safety mechanisms in real-time.
• Detect misuse, prevent abuse, and enforce policies across the stack.
• Collaborate with research and operations teams to harden models and tooling.

Conhecimentos

Python

TypeScript

Strong communication

Explain complex concepts

Adversarial inputs

Formação académica

Bachelor’s degree in Computer Science or related field

Ferramentas

Internal tooling

Descrição da oferta de emprego

Anthropic in the United Kingdom is seeking a software engineer for the Safeguards team to build safety and oversight mechanisms for AI systems. You will monitor models, prevent misuse, and surface abuse patterns to researchers and analysts for action.

Responsibilities include building scalable detection systems, real-time defenses, and internal tooling, with a focus on safety, transparency, and policy enforcement across the stack. Premier compensation and relocation support are offered.