AI Safety Expert – English, Gujarati

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

📋 Description

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

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

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

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

• Evaluate AI outputs related to sensitive subjects such as bias, misinformation, and harmful actions.

• Broaden evaluation coverage and discover vulnerabilities that automated tests may overlook.

⛳️ Requirements

• Must possess native fluency in both English and Gujarati.

• Strong discernment regarding language and content, including assessing the accuracy, completeness, and appropriateness of AI-generated responses.

• Capability to identify subtle mistakes, inconsistencies, and gaps.

• Consistent adherence to guidelines and quality standards is essential.

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

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

• Engagement as an independent contractor is required.

• Candidates must not be on an H1-B or STEM OPT visa.

• Preferred: experience with jailbreak datasets, prompt injection, RLHF/DPO attacks, or model extraction.

• Preferred: experience in penetration testing, exploit development, or reverse engineering.

• Preferred: experience in harassment/disinformation probing, abuse analysis, or testing conversational AI.

• Preferred: background in psychology, acting, or writing for unconventional adversarial thinking.

🏝️ Benefits

• Enjoy a fully remote position that allows you to work on your own schedule.

• Receive weekly payments through Stripe or Wise based on the services provided.

• Participation in higher-sensitivity projects is optional.

• Access clear guidelines and wellness resources for handling sensitive content.

• Reasonable accommodations available upon request.

• Gain experience in human data-driven AI red teaming.

• Play a direct role in enhancing the robustness, safety, and trustworthiness of AI systems.

• Earn referral payments of up to $90 for each successful referral.