AI Red-Teamer | $111 Remote

Position: AI Red-Teamer — Adversarial AI Testing (Novice)

Type: Hourly contract

Compensation

$54–$111/hour

Location

Remote

Commitment: 10–40 hours/week

Role Responsibilities

Conduct adversarial testing on AI models, including jailbreaks, prompt injections, misuse cases, and exploit discovery.Generate high-quality human data by annotating failures, classifying vulnerabilities, and flagging systemic risks.Apply structured red-teaming methodologies using established taxonomies, benchmarks, and testing playbooks.Document findings in a reproducible manner by producing reports, datasets, and actionable attack cases.Support multiple testing efforts across projects, including LLM safety testing and socio-technical abuse scenarios.Surface vulnerabilities that automated evaluation systems fail to detect.

Requirements

Prior experience in AI red-teaming, adversarial testing, cybersecurity, or socio-technical risk analysis ORa strong AI background or education with the ability to learn red-teaming methodologies quickly.Strong adversarial mindset with curiosity and persistence in stress-testing systems.Ability to apply structured frameworks rather than relying on ad-hoc testing methods.Clear written communication skills for explaining risks to technical and non-technical stakeholders.High adaptability and comfort working across multiple projects and evolving requirements.Ability to work independently in a remote, project-based environment.

Application Process

Upload resumeInterview (15 min)Submit form