Research Engineer, Cybersecurity Reinforcement Learning
AnthropicZürich, Switzerland
AI safety & policy
Information security
Full-time
AI safety & policy
Information security
Full-time
Routes to impact
Direct high impact on an important cause
Description
Develop and deploy reinforcement learning environments and experiments to improve AI systems for defensive cybersecurity tasks.
- Design and implement RL environments, experiments, and evaluations
- Deliver research outputs into production training runs
- Build agentic integrations for autonomous security investigation and action
- Collaborate with researchers, engineers, and cybersecurity specialists
- Visa sponsorship available, with reasonable efforts to support successful candidates
This text was generated by AI. If you notice any inconsistencies, please let us know using this form.
