AI Safety Expert, English, Odia

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

📋 Description

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

• Document failures, categorize vulnerabilities, and highlight systemic risks.

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

• Generate reproducible reports, datasets, and attack scenarios.

• Evaluate AI outputs related to sensitive issues such as bias, misinformation, and harmful behaviors.

• Identify vulnerabilities that automated tests may overlook.

• Broaden evaluation coverage to minimize unexpected issues in production.

• Enhance customer AI systems through data-driven human red teaming.

⛳️ Requirements

• Proficient/native fluency in English and Odia is essential.

• Strong discernment regarding language and content, including assessing AI responses for accuracy, completeness, and appropriateness.

• Capability to spot subtle errors, inconsistencies, and gaps.

• Consistent adherence to guidelines and quality standards.

• Ability to clearly articulate reasoning to both technical and non-technical stakeholders.

• Flexibility to adapt across various projects, task types, and clients.

• Engagement as an independent contractor.

• Must not require H1-B or STEM OPT visa support.

• Preferred areas of expertise: adversarial machine learning, cybersecurity, socio-technical risk, or creative probing.

🏝️ Benefits

• Completely remote position.

• Flexible scheduling options.

• Participation in higher-sensitivity projects is optional.

• Clear guidelines and wellness resources available for sensitive-content tasks.

• Weekly payments through Stripe or Wise.

• Competitive compensation.

• Collaborate with top researchers in the field.

• Referral program: earn up to $90 for each successful referral, subject to limits.

• Reasonable accommodations available upon request.