Research Engineer, Cybersecurity RL (Reinforcement Learning)
Zürich, CH
Posted 1mo ago
Job Location
Zürich, CH
Tech Stack
Remote Work Policy
On-site
Categories
AI Research Engineer
About the job
At Anthropic, we are pioneering new frontiers in AI that have the potential to greatly benefit society. However, developing advanced AI also comes with risks if not properly safeguarded. As a Research Engineer, you'll help to safely advance the capabilities of our models in incident response, security analysis, vulnerability remediation, and other areas of defensive cybersecurity. This role blends research and engineering, requiring you to both develop novel approaches and realize them in code. Your work will include designing and implementing RL environments, conducting experiments and evaluations, delivering your work into production training runs, and collaborating with other researchers, engineers, and cybersecurity specialists across and outside Anthropic. This role requires ML experience combined with domain expertise in cybersecurity. You might be an ML researcher with a history of cybersecurity work, or a security professional with a background in ML.
Responsibilities
- Partner with researchers and safety teams to understand analytical needs and build solutions.
- Develop agentic integrations for autonomous investigation and action by AI systems.
- Contribute to the strategic direction of the team, including decisions on what to build, partner on, and invest in.
- Participate in an on-call rotation.
Requirements
- Experience with machine learning.
- Experience in cybersecurity research.
- Strong software engineering skills.
- Ability to balance research exploration with engineering implementation.
- Passion for AI's potential and commitment to developing safe and beneficial systems.
- Professional experience in security engineering, fuzzing, detection and response, or other applied defensive work.
- Experience participating in or building CTF competitions and cyber ranges.
- Academic research experience in cybersecurity or other experimental & research background.
- Familiarity with RL techniques and environments.
- Familiarity with LLM training methodologies.