Research Engineer, AI Monitoring
Anthropic · London, UK
Frontier labonsite
At a glance
Highlights
- Build classifiers that block unsafe agent actions like sandbox escapes in real time.
- Deploy safety classifiers into RL, evals and internal deployments at huge scale.
- Harden classifiers with red teaming and feed findings into safer designs.
What they offer
- Competitive compensation and benefits
- Optional equity donation matching
- Generous vacation and parental leave
- Flexible working hours
- Lovely office space for collaboration
Ideal candidate
Organized, communicative engineer motivated by AI safety who enjoys owning ambiguous problems end-to-end and directing AI agents to test and ship impactful defenses.
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
Lab profile
About Anthropic
AI safety company building reliable, interpretable and steerable frontier AI systems.
What they build
- Claude
- Claude API
- Claude Code
Known for
- AI safety and alignment
- Model interpretability research
- Frontier LLM development
Key facts
- Founded in 2021
- Headquartered in San Francisco, California
- Backed by Amazon and Google
Posted · Last seen