Red Team Analyst | Remote

Crossing Hurdles; United States; On-site; USD 70,000 - 90,000; Full time

Job summary

A leading AI safety organization in the United States is seeking candidates with a strong adversarial mindset to identify vulnerabilities in cutting-edge AI systems. Responsibilities include annotating model failures, conducting evaluations, and producing actionable insights for clients. Candidates must demonstrate excellent communication skills, an ability to navigate multiple safety domains, and thrive in a fast-paced remote work environment. This is an exciting opportunity to contribute to significant projects in AI safety.

Qualifications

• Strong adversarial mindset with the ability to push systems to breaking points.
• Experience applying structured evaluation frameworks and benchmarks.
• Clear written communication skills for technical and non-technical audiences.
• Ability to operate across multiple safety domains and evolving project scopes.
• Comfortable working independently in a fast-paced remote environment.

Responsibilities

• Annotate model failures and classify vulnerabilities in frontier AI systems.
• Identify systemic risks and document reproducible attack cases.
• Apply structured taxonomies, benchmarks, and safety frameworks.
• Produce clear reports, datasets, and actionable insights for customers.
• Support diverse projects including jailbreak testing and socio-technical abuse evaluations.

Skills

Adversarial mindset

Structured evaluation frameworks

Clear written communication

Ability to operate across multiple safety domains

Comfort in fast-paced environment

Job description

• Annotate model failures and classify vulnerabilities in frontier AI systems.
• Identify systemic risks and document reproducible attack cases.
• Apply structured taxonomies, benchmarks, and safety frameworks.
• Produce clear reports, datasets, and actionable insights for customers.
• Support diverse projects including jailbreak testing and socio technical abuse evaluations.

Requirements

• Strong adversarial mindset with the ability to push systems to breaking points.
• Experience applying structured evaluation frameworks and benchmarks.
• Clear written communication skills for technical and non technical audiences.
• Ability to operate across multiple safety domains and evolving project scopes.
• Comfort working independently in a fast paced remote environment.