Staff / Software Engineer (Safeguards)

Anthropic; York and North Yorkshire; On-site; GBP 110,000 - 160,000; Full time

Benefits offered by this job

Comprehensive health insurance

Fertility benefits via Carrot Fertilty

Paid parental leave 22 weeks

Flexible paid time off

Job summary

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.

Qualifications

• 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.

Responsibilities

• 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.

Skills

Python

TypeScript

Strong communication

Explain complex concepts

Adversarial inputs

Education

Bachelor’s degree in Computer Science or related field

Tools

Internal tooling

Job description

• We are looking for 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
• Develop monitoring systems to detect unwanted behaviors from our API partners and potentially take automated enforcement actions; surface these in internal dashboards to analysts for manual review
• Build abuse detection mechanisms and infrastructure
• Surface abuse patterns to our research teams to harden models at the training stage
• Build robust and reliable multi-layered defenses for real-time improvement of safety mechanisms that work at scale

Benefits

• Comprehensive health, dental, and vision insurance for you and your dependents
• Inclusive fertility benefits via Carrot Fertility
• 22 weeks of paid parental leave
• Flexible paid time off and absence policies
• Mental health support for you and your dependents
• Competitive salary and equity packages
• Optional equity donation matching at a 1:1 ratio, up to 25% of your equity grant
• Retirement plans with competitive matching
• Life and income protection plans
• $500/month flexible wellness and time saver stipend
• Commuter benefits
• Annual education stipend
• Home office stipends
• Relocation support for those moving for Anthropic
• Daily meals and snacks in the office

Proficiency in Python and TypescriptStrong communication skills and ability to explain complex technical concepts to non-technical stakeholdersAbility to work across the stackBachelor’s degree in Computer Science, Software Engineering or comparable experienceWe encourage you to apply even if you do not believe you meet every single qualificationHave experience with integrity, spam, fraud, or abuse detection and mitigation8+ years of experience in a software engineering positionHave experience building trust and safety detection mechanisms and intervention for AI/ML systemsHave experience with prompt engineering, jailbreak attacks, and other adversarial inputsHave worked closely with operational teams to build custom internal tooling