AI Safety Expert – English, Gujarati

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

📋 Description

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

• Generate annotated human data by identifying failures, categorizing vulnerabilities, and highlighting systemic risks.

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

• Create reproducible reports, datasets, and attack case studies for clients.

• Analyze AI outputs related to sensitive topics, including bias, misinformation, and harmful behaviors.

• Contribute to the expansion of evaluation coverage and the enhancement of customer AI systems.

⛳️ Requirements

• Proficient fluency in both English and Gujarati is essential.

• Strong discernment regarding language and content.

• Capability to evaluate whether AI responses are accurate, complete, and suitable, with the ability to articulate the reasoning behind assessments.

• Attention to detail to identify subtle errors, inconsistencies, and gaps.

• Consistent adherence to guidelines and quality standards.

• Skill in clearly articulating reasoning to both technical and non-technical audiences.

• Flexibility to adapt across various projects, tasks, and clientele.

• Must operate as an independent contractor.

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

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

• Preferred qualifications: background in cybersecurity, including penetration testing, exploit development, or reverse engineering.

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

• Preferred qualifications: experience in psychology, acting, or writing to foster unconventional adversarial thinking.

🏝️ Benefits

• Fully remote position.

• Flexible working hours; complete tasks according to your own schedule.

• Weekly compensation via Stripe or Wise.

• Competitive salary.

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

• Direct involvement in enhancing the robustness, safety, and trustworthiness of AI systems.

• Collaboration with leading researchers in the field.

• Reasonable accommodations available upon request.