AI Safety Expert, English, Portuguese

This is a fully remote position, open to applicants in United States.

📋 Description

• Conduct red team assessments on conversational AI models and agents by utilizing jailbreaks, prompt injections, misuse scenarios, bias exploitation, and multi-turn manipulation techniques.

• Generate human data through annotating failures, classifying vulnerabilities, and identifying systemic risks.

• Implement taxonomies, benchmarks, and playbooks to ensure consistent testing practices.

• Create reproducible reports, datasets, and attack scenarios.

• Discover vulnerabilities that automated testing may overlook.

• Broaden evaluation coverage while minimizing unexpected issues in production.

• Enhance customer AI systems through adversarial testing methodologies.

⛳️ Requirements

• Native proficiency in both English and Portuguese (excluding Brazilian Portuguese).

• Previous experience in red teaming related to AI adversarial work, cybersecurity, or socio-technical probing.

• Capability to adversarially probe AI systems and push them to their limits.

• Familiarity with frameworks or benchmarks for structured testing approaches.

• Competence in clearly communicating risks to both technical and non-technical audiences.

• Flexibility to adapt across various projects and clients.

• Status as an independent contractor.

• No need for H1-B or STEM OPT sponsorship.

• Preferred qualifications include expertise in adversarial machine learning, cybersecurity, socio-technical risk, and creative probing techniques.

🏝️ Benefits

• Fully remote working environment.

• Flexible and self-managed schedule.

• Participation in higher-sensitivity projects is optional.

• Clear guidelines and wellness resources available for sensitive assignments.

• Weekly payments processed through Stripe or Wise.

• Competitive compensation.

• Opportunity to collaborate with leading researchers in the field.

• Referral fees of up to $180 for each successful referral.