AI Safety Expert, English, Malay

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

📋 Description

• Conduct red team assessments on conversational AI models and agents.

• Evaluate vulnerabilities through testing of jailbreaks, prompt injections, misuse cases, bias exploitation, and multi-turn manipulations.

• Create human data by annotating errors and categorizing vulnerabilities.

• Identify and flag systemic risks.

• Utilize taxonomies, benchmarks, and playbooks to ensure consistent testing methodologies.

• Generate reproducible reports, datasets, and actionable attack scenarios.

• Investigate AI systems for vulnerabilities that automated tests may overlook.

• Increase evaluation coverage and minimize unexpected issues in production.

⛳️ Requirements

• Fluent or native proficiency in both English and Malay.

• Previous experience in red teaming within AI adversarial contexts, cybersecurity, or socio-technical probing.

• Proficient in probing AI models utilizing jailbreaks, prompt injections, misuse cases, bias exploitation, and multi-turn manipulations.

• Capable of annotating failures, categorizing vulnerabilities, and identifying systemic risks.

• Familiarity with following taxonomies, benchmarks, and playbooks.

• Skilled in producing reproducible reports, datasets, and attack scenarios.

• Ability to communicate risks effectively to both technical and non-technical audiences.

• Adaptable to various projects and clients.

• Candidates must not require H1-B or STEM OPT sponsorship.

🏝️ Benefits

• Fully remote position.

• Flexible scheduling options.

• Weekly payments processed through Stripe or Wise.

• Project durations may be adjusted based on requirements and performance.

• Participation in higher-sensitivity projects is optional.

• Access to clear guidelines and wellness resources for work involving sensitive content.

• Reasonable accommodations available upon request.

• Competitive salary.

• Referral bonuses of up to $100 for each successful referral.