Cyber Evaluations Engineer

Anthropic
San Francisco, California, United States
Full Time
Hybrid
Mid
USD 300,000 – 405,000
Bachelor Degree
Technology Information Technology Telecommunications

Posted 3 days ago

Apply to this job and hundreds more automatically

Get Started
Excellent 4.7

Job summary

Anthropic seeks Cyber Evaluations Engineers to develop and execute evaluations assessing cyber-relevant capabilities, robustness, and safeguards of AI models. Responsibilities include designing tests, analyzing results, developing detection probes, and collaborating on safeguard improvements, requiring cybersecurity experience, evaluation building, and strong communication skills.

Responsibilities

Design and execute cyber-relevant capability and safety evaluations to assess model risks and safeguard robustness. Collaborate with policy and engineering teams to develop detection architectures and translate evaluation findings into actionable security improvements.

Qualifications

Adversarial Data Analysis Cybersecurity Cybersecurity Testing Detection Content Authoring Evaluation Design ML Evaluation Frameworks Python Security Research Threat Detection Vulnerability Research

Requires hands-on cybersecurity experience, proficiency in Python, and a background in building evaluations or test suites for software or ML systems. Candidates should possess strong communication skills and the ability to work effectively with cross-functional stakeholders.

English

Benefits

  • Competitive compensation
  • Equity donation matching
  • Generous vacation
  • Parental leave
  • Flexible working hours

Company

Anthropic

Anthropic

Research Services
Location
San Francisco, California, United States

Apply to this job and hundreds more automatically

Get Started
Excellent 4.7
Pete DeQuarto avatar
Pete DeQuarto

AIApply is a total game-changer. Thanks to Auto-Apply, I have been applying to jobs I would never even have come across otherwise!

Akarshak Tanwar avatar
Akarshak Tanwar

In one week I applied to over 150 jobs and locked in 2 confirmed interviews, with a support team that was quick to respond. The auto-apply feature is fascinating and a real pleasure to use!

JC
Julian Carlin

It really worked. In under 48 hours it had applied to 100 jobs on my behalf without any time or effort from me. I am looking forward to seeing how it keeps improving.