AI Red Team Simulation Researcher

About the role

Responsibilities

• Design automated red-teaming simulation frameworks for large language models
• Develop adversarial attack taxonomies and scenario generation pipelines
• Build evaluation systems combining automated scoring and human review sampling
• Publish research findings internally and externally
• Advise client AI teams on red-teaming methodology and risk prioritization

Requirements

• PhD or 6+ years research experience in ML safety, security, or NLP
• Deep understanding of adversarial attacks on language models
• Strong Python and PyTorch skills
• Track record of research publication preferred
• Ability to communicate risk findings to non-technical executive stakeholders

Benefits

• Remote-first research environment
• Top-of-market total compensation including equity
• Dedicated research time with no KPI constraints
• Annual conference travel budget ($5,000)
• Full health, dental, and vision with premium coverage

Keep exploring related roles

Use these topic pages to discover more roles in the same hiring cluster.