Research Engineer, Cybersecurity RL (Reinforcement Learning)
Zürich, CH
Posted 7d ago
Remote Work Policy
On-site
Categories
AI Research Engineer
About the job
The Security team at Anthropic is dedicated to protecting AI systems and maintaining user trust. As a Research Engineer on this team, you will play a crucial role in advancing the capabilities of our models in areas such as secure coding, vulnerability remediation, and other defensive cybersecurity measures. This position uniquely combines research and engineering, requiring you to develop novel approaches and implement them in code. Your responsibilities will include designing and building Reinforcement Learning (RL) environments, conducting experiments and evaluations, integrating your work into production training runs, and collaborating with researchers, engineers, and cybersecurity specialists both internally and externally.
Responsibilities
- Design, build, and maintain RL environments and evaluations for secure coding, vulnerability discovery/remediation, and defensive security tasks.
- Conduct experiments to develop and test new training approaches, and integrate successful results into production training runs.
- Collaborate with internal and external cybersecurity experts to align environments and evaluations with realistic defensive workflows.
- Contribute to the team's strategic direction, including decisions on development, partnerships, and investments.
- Participate in an on-call rotation as needed.
Requirements
- Experience in cybersecurity research or applied security work.
- Experience with machine learning.
- Ability to balance research exploration with engineering implementation.
- Commitment to developing safe and beneficial AI systems.