Cybersecurity Research Engineer - Remote

Overview

As a Cybersecurity Research Engineer at Anthropic, you will lead research to baseline current models and test whether future frontier capabilities could cause significant harm, focusing on the intersection of AI and cybersecurity.

In Short

• Design and analyze scientific experiments related to large language models.
• Lead technical design discussions for infrastructure support.
• Collaborate on maintaining evaluations codebase.
• Work with external partners on novel evaluations.
• Partner with cross-functional teams to advance safety missions.
• Strong software engineering or AI/ML research experience required.
• Interest in societal impacts of AI is essential.
• Clean, well-documented Python code writing is expected.
• Strong problem-solving skills and results-oriented mindset are necessary.
• Excellent communication skills are crucial for collaboration.

Requirements

• Experience in offensive cybersecurity or AI/ML research.
• Familiarity with large language models and their applications.
• Ability to balance research goals with engineering constraints.
• Experience with training or evaluating models for cyber capabilities.
• Participation in CTF challenges or professional pentesting is a plus.
• Experience in developing evaluations or benchmarks for AI models.

Benefits

• Competitive compensation and benefits.
• Optional equity donation matching.
• Generous vacation and parental leave.
• Flexible working hours.
• Collaborative office space in San Francisco.