ML/Research Engineer (Safeguards)

Anthropic; York and North Yorkshire; On-site; GBP 90,000 - 120,000; Full time

Benefits offered by this job

Health insurance

Parental leave

Flexible PTO

Mental health support

Equity packages

Equity donation matching

Retirement plan

Life insurance

Commuter benefits

Education stipend

Home office stipend

Relocation support

On-site meals

Job summary

Anthropic in the United Kingdom seeks ML Engineers and Research Engineers to build safeguards against misuse of AI systems, identifying harmful use and ensuring models behave responsibly. You will develop classifiers and monitoring across contexts, study adversarial robustness, and deploy mitigations for prompt injection.

Strong Python skills, 4+ years in ML, and the ability to explain complex ideas to non-technical stakeholders are required.

Qualifications

• Strong Python skills and experience building ML systems.
• Experience mitigating AI misuse and building safeguarding classifiers.
• Ability to explain complex technical concepts to non-technical stakeholders.

Responsibilities

• Develop classifiers to detect misuse and anomalous behavior at scale.
• Build systems to monitor harms across exchanges and aggregate signals.
• Evaluate and mitigate risks in agentic products and defend against prompt injection.

Skills

Python

ML systems

4+ years experience

Communication

Education

Bachelor's degree or equivalent

Job description

• We are looking for ML Engineers and Research Engineers to help detect and mitigate misuse of our AI systems
• As a member of the Safeguards ML team, you will build systems that identify harmful use—from individual policy violations to sophisticated, coordinated attacks—and develop defenses that keep our products safe as capabilities advance
• You will also work on systems that protect user wellbeing and ensure our models behave appropriately across a wide range of contexts
• This work feeds directly into Anthropic’s Responsible Scaling Policy commitments
• Develop classifiers to detect misuse and anomalous behavior at scale. This includes developing synthetic data pipelines for training classifiers and methods to automatically source representative evaluations to iterate on
• Build systems to monitor for harms that span multiple exchanges, such as coordinated cyber attacks and influence operations, and develop new methods for aggregating and analyzing signals across contexts
• Evaluate and improve the safety of agentic products—developing both threat models and environments to test for agentic risks, and developing and deploying mitigations for prompt injection attacks
• Conduct research on automated red-teaming, adversarial robustness, and other research that helps test for or find misuse

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

Have strong communication skills and ability to explain complex technical concepts to non-technical stakeholdersHave proficiency in Python and experience building ML systemsHave 4+ years of experience in ML engineering, research engineering, or applied research, in academia or industryAre worried about misuse risks of AI systems, and want to work to mitigate themAre comfortable working across the research-to-deployment pipeline, from exploratory experiments to production systemsInterpretability or probesBuilding classifiers, anomaly detection systems, or behavioral MLLanguage modeling and transformersAdversarial machine learning or red-teamingWe require at least a Bachelor’s degree in a related field or equivalent experienceReinforcement learningHigh-performance, large-scale ML systems