5 hours ago
Zürich, SwitzerlandAny Level
Responsibilities
- Design, build, and maintain reinforcement learning environments and evaluations for secure coding, vulnerability discovery, remediation, and defensive security tasks.
- Run experiments on new training approaches and deliver successful results into production training runs.
- Collaborate with Anthropic researchers, engineers, security specialists, and external cybersecurity organizations.
- Contribute to strategic decisions about team priorities, 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.
- Preferred: professional experience in security engineering, fuzzing, detection and response, or other applied defensive work.
- Preferred: experience participating in or building CTF competitions and cyber ranges.
- Preferred: academic research experience in cybersecurity.
- Preferred: familiarity with reinforcement learning techniques and environments.
- Preferred: familiarity with LLM training methodologies.
- Bachelor’s degree or an equivalent combination of education, training, and/or experience in a relevant field.
Benefits
- Visa sponsorship is offered, with limitations depending on the role and candidate, and immigration-lawyer support is available.
- Hybrid work policy: staff are expected to work from an Anthropic office at least 25% of the time, though some roles may require more office time.
- Competitive compensation and benefits.
- Optional equity donation matching.
- Generous vacation and parental leave.
- Flexible working hours and office collaboration space.
Categories
About Anthropic
We're an AI research company that builds reliable, interpretable, and steerable AI systems. Our first product is Claude, an AI assistant for tasks at any scale. Our research interests span multiple areas including natural language, human feedback, scaling laws, reinforcement learning, code generation, and interpretability.