AI Safety Expert – English, Tamil

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

📋 Description

• Conduct red-team evaluations of conversational AI models and agents by utilizing jailbreaks, prompt injections, misuse scenarios, bias exploitation, and multi-turn manipulations.

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

• Adhere to established taxonomies, benchmarks, and playbooks to ensure consistency in testing.

• Generate reproducible reports, datasets, and attack scenarios.

• Assess AI outputs concerning sensitive matters such as bias, misinformation, and harmful actions.

• Broaden evaluation coverage to identify vulnerabilities missed by automated tests.

• Collaborate on initiatives aimed at training and enhancing advanced AI systems.

⛳️ Requirements

• Proficient/native speaker in both English and Tamil.

• Strong discernment regarding language use and content quality.

• Capability to evaluate the accuracy, completeness, and appropriateness of AI responses.

• Keen attention to detail to identify subtle mistakes, inconsistencies, and omissions.

• Consistent adherence to guidelines and quality standards.

• Ability to articulate reasoning effectively to both technical and non-technical audiences.

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

• Must possess independent contractor status.

• Not eligible for H1-B or STEM OPT sponsorship.

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

🏝️ Benefits

• Fully remote position.

• Flexible scheduling.

• Weekly payments through Stripe or Wise.

• Competitive compensation.

• Opportunity to gain experience in human data-driven AI red teaming.

• Direct contribution to enhancing the robustness, safety, and trustworthiness of AI systems.

• Collaboration with top researchers in the field.

• Reasonable accommodations available upon request.

• Referral bonuses of up to $90 for each successful referral.