AI Red Team Analyst; LLM Safety & Adversarial Testing | Remote

Type: Hourly contract

Compensation: $26/hour

Location: Remote

Commitment: 10–40 hours/week

• Red-team conversational AI systems using jailbreaks, prompt injections, misuse cases, bias exploitation, and multi-turn adversarial strategies.
• Generate high-quality human data by annotating failures, classifying vulnerabilities, and flagging systemic risks.
• Follow structured taxonomies, benchmarks, and testing playbooks to ensure consistency and coverage.
• Document findings reproducibly through reports, datasets, and adversarial test cases.
• Evaluate AI outputs across sensitive or high-risk scenarios in alignment with defined safety guidelines.

• Native-level fluency in both English and Spanish.
• Prior experience in AI red teaming, adversarial AI testing, cybersecurity, or socio-technical risk analysis.
• Strong analytical and adversarial thinking skills.
• Ability to apply structured evaluation frameworks and benchmarks.
• Excellent written communication and documentation skills.
• Comfortable working independently in a remote, project-based environment.