AI Safety Expert, English – Kannada

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

📋 Description

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

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

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

• Generate reproducible reports, datasets, and attack scenarios.

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

• Identify vulnerabilities overlooked by automated testing procedures.

• Broaden evaluation coverage to minimize unexpected outcomes in production.

• Enhance customers' AI systems through data-driven red teaming efforts.

⛳️ Requirements

• Native proficiency in English and Kannada.

• Strong discernment regarding language and content.

• Capability to evaluate whether AI responses are accurate, comprehensive, and suitable, along with the ability to articulate reasoning.

• Meticulous attention to detail concerning subtle errors, inconsistencies, and omissions.

• Consistent adherence to guidelines and quality standards.

• Ability to communicate reasoning effectively to both technical and non-technical stakeholders.

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

• Status as an independent contractor.

• Not eligible as an H1-B or STEM OPT candidate.

• Preferred specialties include adversarial ML, cybersecurity, socio-technical risk, or creative probing.

🏝️ Benefits

• Completely remote position.

• Flexibility to work according to your own schedule.

• Weekly payments via Stripe or Wise.

• Optional participation in higher-sensitivity projects.

• Access to clear content guidelines and wellness resources.

• Competitive compensation.

• Opportunity to collaborate with leading researchers.

• Referral bonuses of up to $90 for each successful referral (certain limits apply).