Research Engineer, AI Monitoring

Anthropic Limited

Greater London

Hybrid

GBP 90,000 - 150,000

Full time

2 days ago
Be an early applicant

Get a reply from this employer

Your resume and cover letter, tailored to exactly what they’re hiring for.

Get past ATS filters

Job summary

Anthropic Limited is seeking engineers/researchers to design and deploy safety classifiers for real-time agent actions. You will train models, run experiments, and own classifier performance across latency, cost, and reliability.

The role blends research and production engineering, with emphasis on prioritisation and clear communication across teams. You’ll work with prompts, probes, and model internals to improve guardrails while supporting scalable, safe AI systems.

Qualifications

  • Experience leading ambiguous technical projects and setting direction for other engineers or researchers.
  • Experience evaluating large language models, developing classifiers, or operating high-scale production systems where requirements change quickly.
  • Experience building detection systems where true positives are rare and false positives are costly.

Responsibilities

  • Design, train, and evaluate classifiers that detect unsafe agent actions in real time, owning pieces such as prompted models, trained classifiers, or probes on model internals.
  • Deploy, tune and operate these classifiers in the critical path of internal agents, RL training, and evaluations, and own their accuracy, reliability, latency, cost, and failure behaviour.
  • Build datasets, labelling pipelines, and evaluations that allow us to measure and improve our classifiers and harm taxonomies.
  • Partner with red teaming colleagues to stress-test our classifiers, and harden them against what they find.
  • Work with teams whose agents, environments, and evaluations we run on, ensuring false positives are fixed quickly without weakening protection.
  • Contribute to the team's direction, including what to build, what to partner on, and where to invest.

Skills

Leading technical projects
Evaluating language models
Low-latency services
LLM inference
Probing/model internals

Education

Bachelor's degree or higher

Job description

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.

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 product work. These classifiers need to cover a huge volume of traffic while operating within cost, latency and availability constraints.

Day to day, much of our work is done with Claude: you'll direct agents to run experiments and ship code, and review what they produce. That moves the hard part of the job towards deciding what to do and in what order. Additionally, organisation, communication, and prioritisation skills matter a great deal as our classifiers sit in the path of many other teams' work.

Key responsibilities

Design, train, and evaluate classifiers that detect unsafe agent actions in real time, owning pieces such as prompted models, trained classifiers, or probes on model internals

Deploy, tune and operate these classifiers in the critical path of internal agents, RL training, and evaluations, and own their accuracy, reliability, latency, cost, and failure behaviour

Build the datasets, labelling pipelines, and evaluations that allow us to measure and improve our classifiers and harm taxonomies

Partner with red teaming colleagues to stress-test our classifiers, and harden them against what they find

Work with the teams whose agents, environments, and evaluations we run on, so that false positives get fixed quickly without weakening protection

Contribute to the team's direction, including what to build, what to partner on, and where to invest

Ability to organise and prioritise several parallel streams of work, and to communicate clearly with the teams that work affects

Ability to critically review code and experiment results, including work produced by AI agents

Sincere interest in developing safe and beneficial AI systems

Preferred qualifications

Experience leading ambiguous technical projects and setting direction for other engineers or researchers

Experience evaluating large language models, developing classifiers, or operating high-scale production systems where requirements change quickly

Experience building detection systems where true positives are rare and false positives are costly, such as abuse, fraud, spam, or intrusion detection

Experience running low-latency, high-availability services that other systems depend on, including being on call for them

Experience fine-tuning language models, or working with probes and other methods that read model internals

Experience with LLM inference or serving infrastructure, or with integrating new components into training infrastructure

Background in security, such as sandboxing or detection and response

Familiarity with research on AI control, scalable oversight, agent safety, or reinforcement learning

The annual compensation range for this role is listed below.

For sales roles, the range provided is the role’s On Target Earnings ("OTE") range, meaning that the range includes both the sales commissions/sales bonuses target and annual base salary for the role.

Logistics

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

Location-based hybrid policy: Currently, we expect all staff to be in one of our offices at least 25% of the time. However, some roles may require more time in our offices.

Visa sponsorship:We do sponsor visas! However, we aren't able to successfully sponsor visas for every role and every candidate. But if we make you an offer, we will make every reasonable effort to get you a visa, and we retain an immigration lawyer to help with this.

For roles performing work in California: We will consider for employment all qualified applicants, including those with arrest or conviction records or criminal histories, in a manner consistent with the requirements of applicable state and local laws, including the San Francisco Fair Chance Ordinance, the City of Los Angeles’ Fair Chance Initiative for Hiring Ordinance, the Los Angeles County Fair Chance Ordinance for Employers, and the California Fair Chance Act.

We encourage you to apply even if you do not believe you meet every single qualification. Not all strong candidates will meet every single qualification as listed. Research shows that people who identify as being from underrepresented groups are more prone to experiencing imposter syndrome and doubting the strength of their candidacy, so we urge you not to exclude yourself prematurely and to submit an application if you're interested in this work. We think AI systems like the ones we're building have enormous social and ethical implications. We think this makes representation even more important, and we strive to include a range of diverse perspectives on our team.Your safety matters to us. To protect yourself from potential scams, remember that Anthropic recruiters only contact you from@anthropic.comemail addresses. In some cases, we may partner with vetted recruiting agencies who will identify themselves as working on behalf of Anthropic. Be cautious of emails from other domains. Legitimate Anthropic recruiters will never ask for money, fees, or banking information before your first day. If you're ever unsure about a communication, don't click any links—visit anthropic.com/careers directly for confirmed position openings.

How we're different

We believe that the highest-impact AI research will be big science. At Anthropic we work as a single cohesive team on just a few large-scale research efforts. And we value impact — advancing our long‑term goals of steerable, trustworthy AI — rather than work on smaller and more specific puzzles. We view AI research as an empirical science, which has as much in common with physics and biology as with traditional efforts in computer science. We're an extremely collaborative group, and we host frequent research discussions to ensure that we are pursuing the highest‑impact work at any given time. As such, we greatly value communication skills.

The easiest way to understand our research directions is to read our recent research. This research continues many of the directions our team worked on prior to Anthropic, including: GPT‑3, Circuit‑Based Interpretability, Multimodal Neurons, Scaling Laws, AI & Compute, Concrete Problems in AI Safety, and Learning from Human Preferences.

Come work with us!

Anthropic is a public benefit corporation headquartered in San Francisco. We offer competitive compensation and benefits, optional equity donation matching, generous vacation and parental leave, flexible working hours, and a lovely office space in which to collaborate with colleagues. Guidance on Candidates' AI Usage:Learn about our policy for using AI in our application process.

Get your free, confidential resume review.

or drag and drop your file here.

Similar jobs

Similar jobs worth comparing

Staff Software Security Engineer
Staff Software Security Engineer

Anthropic Limited • Greater London

On-site
GBP 255,000 - 325,000
Competitive compensation
Equity donation matching (optional)
Generous vacation & parental leave
+1
Principal Engineer, Privacy
Principal Engineer, Privacy

Borderless • Greater London

Hybrid
GBP 367,000 - 473,000
Engineering Manager, Agent Security Partnerships
Engineering Manager, Agent Security Partnerships

Borderless • Greater London

Hybrid
GBP 306,000 - 367,000
Visa sponsorship available
Competitive compensation
Generous vacation
Staff Software Engineer, Continuous Integration
Staff Software Engineer, Continuous Integration

Anthropic Limited • City Of London

Hybrid
GBP 325,000 - 390,000
Competitive compensation
Equity donation matching
Generous vacation
+2
Research Engineer, Machine Learning (Reinforcement Learning)New
Research Engineer, Machine Learning (Reinforcement Learning)New

Anthropic Limited • Greater London

Hybrid
GBP 90,000 - 140,000
Visa sponsorship
Hybrid work policy
[Expression of Interest] Research Engineer / Scientist, Alignment - London
[Expression of Interest] Research Engineer / Scientist, Alignment - London

Anthropic Limited • Greater London

Hybrid
GBP 260,000 - 370,000
Competitive compensation
Equity donation matching
Generous vacation and parental leave
+1
Staff+ Software Engineer, Safeguards Infrastructure
Staff+ Software Engineer, Safeguards Infrastructure

Anthropic Limited • City Of London

Hybrid
GBP 325,000 - 395,000
Competitive compensation
Visa sponsorship where eligible
Equity donation matching
+2
Staff Infrastructure Engineer, Cluster Infrastructure
Staff Infrastructure Engineer, Cluster Infrastructure

Anthropic Limited • City Of London

On-site
GBP 325,000 - 485,000
Applied AI Architect, Industries Anthropic
Applied AI Architect, Industries Anthropic

CDFAM - Computational Design Symposium • Greater London

Hybrid
GBP 165,000 - 190,000
Competitive compensation
Equity donation matching
Generous vacation and parental leave
+1
Staff Software Engineer, Infrastructure (Distributed Systems)
Staff Software Engineer, Infrastructure (Distributed Systems)

Anthropic Limited • Greater London

Hybrid
GBP 110,000 - 170,000