AI Safety Expert, English – Punjabi

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

📋 Description

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

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

• Utilize taxonomies, benchmarks, and playbooks to ensure standardized testing procedures.

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

• Analyze AI outputs that involve sensitive subjects such as bias, misinformation, and harmful behaviors.

• Broaden evaluation scope and uncover vulnerabilities that automated tests may overlook.

• Develop artifacts that enhance the security and reliability of customer AI systems.

• Engage in projects focused on training and improving AI systems for Mercor's AI lab and its enterprise partners.

⛳️ Requirements

• Must possess native fluency in both English and Punjabi.

• Demonstrate strong judgment regarding language and content, particularly in evaluating the accuracy, completeness, and appropriateness of AI responses.

• Capable of articulating reasoning effectively to both technical and non-technical audiences.

• Skilled at identifying subtle errors, inconsistencies, and omissions.

• Consistently adhere to guidelines and quality standards.

• Exhibit flexibility across various projects, task types, and client requirements.

• Position available for independent contractor engagement only.

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

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

• Preferred qualifications: background in cybersecurity, inclusive of penetration testing, exploit development, and reverse engineering.

• Preferred qualifications: experience in socio-technical risk assessment, such as harassment/disinformation probing, abuse analysis, and conversational AI testing.

• Preferred qualifications: experience in creative probing through psychology, acting, or writing.

🏝️ Benefits

• Fully remote position.

• Flexibility to work according to your own schedule.

• Project timelines can be extended, shortened, or concluded early based on requirements and performance.

• Receive weekly payments through Stripe or Wise for services rendered.

• Participation in higher-sensitivity projects is optional.

• Access to clear guidelines and wellness resources for projects involving sensitive content.

• Reasonable accommodations available upon request.

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

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

• Collaborate with top researchers in the field.

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