Research Engineer, AI Monitoring
Posted Updated 12
views
Who recruits here
Up to three recruiters at Anthropic with their work email, so you can write to a person.
Available on Pro.
Description
You will build, test, deploy and monitor classifiers that block internal agents from taking dangerous actions across RL, evals and internal deployments. You will combine research on high recall and precision detection with production engineering, working with Claude to run experiments and ship code, and partnering with red teamers and other teams.
Responsibilities
- Design, train, and evaluate classifiers that detect unsafe agent actions in real time
- Deploy, tune and operate classifiers in the critical path of internal agents, RL training, and evaluations
- Own accuracy, reliability, latency, cost, and failure behaviour of classifiers
- Build datasets, labelling pipelines, and evaluations to measure and improve classifiers and harm taxonomies
- Partner with red teaming colleagues to stress-test and harden classifiers
- Work with teams whose agents and environments you run on to fix false positives quickly
- Contribute to the team's direction
Requirements
- Ability to organise and prioritise several parallel streams of work and communicate clearly
- Ability to critically review code and experiment results, including work produced by AI agents
- Sincere interest in developing safe and beneficial AI systems
- Bachelor's degree or equivalent combination of education, training, and/or experience
Benefits
- Optional equity donation matching
- Generous vacation and parental leave
- Flexible working hours
- Visa sponsorship
Skills
Sign in to read and join the discussion.