# Research Engineer, AI Monitoring

**Company**: Anthropic
**Location**: London
**Work arrangement**: hybrid
**Experience**: senior
**Job type**: full-time
**Salary**: £375,000-£640,000 GBP
**Category**: Engineering
**Industry**: Technology
**Wikidata**: https://www.wikidata.org/wiki/Q116758847

**Apply**: https://job-boards.greenhouse.io/anthropic/jobs/5477416008?utm_source=yubhub.co&utm_medium=jobs_feed&utm_campaign=apply
**Canonical**: https://yubhub.co/job/research-engineer-ai-monitoring-477dfdc1-46e/

## Description

Anthropic's mission is to create reliable, interpretable, and steerable AI systems that are safe and beneficial for users and society.

As a Research Engineer, AI Monitoring, you will work on building, testing, deploying, and monitoring classifiers that block internal agents from taking dangerous actions.

The role combines research and production engineering, focusing on designing high recall and high precision classifiers to catch rare, novel, and sometimes adversarial behaviour.

Key responsibilities:

- Design, train, and evaluate classifiers to detect unsafe agent actions in real time

- Deploy, tune, and operate these classifiers in the critical path of internal agents, RL training, and evaluations

- Build datasets, labelling pipelines, and evaluations to measure and improve classifiers and harm taxonomies

- Partner with red teaming colleagues to stress-test classifiers and harden them against findings

- Work with teams whose agents, environments, and evaluations you run on to fix false positives quickly

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

Minimum qualifications:

- Ability to organise and prioritise several parallel streams of work and communicate clearly with affected teams

- 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

- Experience building detection systems where true positives are rare and false positives are costly

- Experience running low-latency, high-availability services that other systems depend on

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

The annual compensation range for this role is £375,000-£640,000 GBP.

For more fresh new jobs, check out [yubhub.co](https://yubhub.co/).

## Skills

### Required
- AI monitoring
- classifier design
- real-time detection
- dataset building
- collaboration

### Nice to have
- large language models
- production systems
- detection systems
- low-latency services
- model fine-tuning

---

Source: [Apply at job-boards.greenhouse.io](https://job-boards.greenhouse.io/anthropic/jobs/5477416008?utm_source=yubhub.co&utm_medium=jobs_feed&utm_campaign=apply)
