FewerJobs.
All jobs

Research Engineer, AI Monitoring

Anthropic - London, UK

Posted Nov 16, 2026

Benefits

Parental leave
Not verified
Non-birth-parent leave
Not verified
Family-building benefits
  • Fertility benefits: Not verified
  • Adoption assistance: Not verified
  • Surrogacy assistance: Not verified
Mental health support
Not verified
Relocation assistance
Not verified
Childcare support
Not verified
Learning budget
Not verified
Verification
Not verified
Salary
GBP 375K-640K From the posting source

Was this benefit information wrong? Tell us.

Role

Seniority
Mid From the posting source

Schedule

Shift type
Not verified
Weekend work
Not verified

Company

Equity
Offered From the posting source

Application

Cover letter
Not verified
Assessment
Not verified
Deadline
Not stated

Where they hire

State eligibility is not yet verified.

About this role

Research Engineer, AI Monitoring London, UK About Anthropic 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. About the role Our team builds, tests, deploys, and monitors the classifiers that block internal agents from taking dangerous actions. These classifiers run across RL, evals, and internal deployments, and are designed to catch things like sandbox escape attempts or exfiltration of sensitive data. When a classifier flags an action, it can block the action before the tool call runs, end the task, and alert a human . This is one layer of a defence-in-depth with several layers that reinforce each other: what our classifiers flag feeds into offline monitoring, and the findings from that go back into better classifiers and safer environment design. The work combines research and production engineering: The research problem is building high recall and high precision classifiers to catch rare, novel, and sometimes adversarial behaviour. There are also several narrow research questions to answer - for example, how to deploy safety classifiers inside training environments without incentivising models to evade them. Some research also builds on the multi-stage designs described in our work on Claude Code auto mode and Constitutional Classifiers . The engineering problem is shipping these classifiers into the critical path of research and

Read the full description at job-boards.greenhouse.io. FewerJobs shows a preview and links to the original posting.

Apply at job-boards.greenhouse.io

Apply link verified; last checked Nov 20, 2026.

What verified means

Verified means a displayed claim has field-level provenance to a source FewerJobs pulled: a government or employer source, or the original job posting. Posting-sourced facts are employer-stated and are labeled separately from government records.

Related jobs