Cybersecurity RL Research Engineer for Safe AI

Anthropic Limited; San Francisco, New York (CA, NY); Hybrid; USD 500,000 - 850,000; Full time

Benefits offered by this job

Competitive compensation

Equity donation matching

Generous vacation and parental leave

Flexible working hours

Office space in San Francisco

Job summary

Anthropic Limited is hiring a Research Engineer for the Cybersecurity RL team within Horizons. You will help safely advance our models in secure coding, vulnerability remediation, and other defensive cybersecurity areas, blending research and engineering.

You will design and implement RL environments, run experiments, push results into production training, and collaborate with researchers, engineers, and cybersecurity specialists across Anthropic.

Qualifications

• Have experience in cybersecurity research.
• Have experience with machine learning.
• Have strong software engineering skills.
• Can balance research exploration with engineering implementation.
• Are passionate about AI's potential and committed to developing safe and beneficial systems.
• Strong candidates may also have: 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.
• Familiarity with RL techniques and environments.
• Familiarity with LLM training methodologies.

Responsibilities

• Design and implement RL environments for secure training.
• Conduct experiments and evaluations of models and defenses.
• Deliver your work into production training runs and pipelines.
• Collaborate with researchers, engineers, and cybersecurity specialists across Anthropic and beyond.

Skills

Cybersecurity research

Machine learning

Software engineering

Research & engineering balance

AI safety focus

Education

Bachelor’s degree

Job description

Anthropic Limited is hiring a Research Engineer for the Cybersecurity RL team within Horizons. You will help safely advance our models in secure coding, vulnerability remediation, and other defensive cybersecurity areas, blending research and engineering.

You will design and implement RL environments, run experiments, push results into production training, and collaborate with researchers, engineers, and cybersecurity specialists across Anthropic.