AI Safety Expert, English, Punjabi

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

📋 Description

• Assess conversational AI models and agents by exploring vulnerabilities such as jailbreaks, prompt injections, misuse scenarios, bias exploitation, and multi-turn manipulation.

• Create human data by annotating errors, categorizing vulnerabilities, and identifying systemic risks.

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

• Generate reproducible reports, datasets, and attack scenarios for clients.

• Evaluate AI outputs on sensitive subjects including bias, misinformation, and harmful behaviors.

• Detect vulnerabilities that automated tests might overlook.

• Increase evaluation coverage while minimizing unexpected outcomes in production.

• Collaborate with top AI researchers on initiatives aimed at training and enhancing cutting-edge AI systems.

⛳️ Requirements

• Proficiency in English and Punjabi is essential.

• Strong discernment regarding language and content, with the ability to evaluate the accuracy, completeness, and appropriateness of AI responses, and articulate the reasoning behind assessments.

• Keen attention to detail, with the ability to identify subtle errors, inconsistencies, and gaps.

• Consistent adherence to guidelines and quality standards.

• Ability to clearly communicate reasoning to both technical and non-technical audiences.

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

• Engagement as an independent contractor is required.

• Must be capable of working without access to confidential or proprietary information from other employers, clients, or institutions.

• H1-B and STEM OPT candidates are not eligible.

• Preferred: experience in adversarial machine learning, including jailbreak datasets, prompt injections, RLHF/DPO attacks, or model extraction.

• Preferred: background in cybersecurity, such as penetration testing, exploit development, or reverse engineering.

• Preferred: experience in socio-technical risk, including harassment/disinformation probing, abuse analysis, or testing of conversational AI.

• Preferred: creative probing experience in fields like psychology, acting, or writing.

🏝️ Benefits

• Fully remote position.

• Flexible work schedule allowing you to manage your own time.

• Weekly payment options via Stripe or Wise.

• Project duration may vary based on requirements and performance.

• Participation in higher-sensitivity projects is optional.

• Clear guidelines for content and access to wellness resources.

• Reasonable accommodations available upon request.

• Competitive compensation.

• Earn up to $90 for each successful referral (referral limits apply).