AI Safety Expert, English – Kannada

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

📋 Description

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

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

• Implement taxonomies, benchmarks, and playbooks to ensure consistent testing.

• Create reproducible reports, datasets, and attack scenarios that clients can act upon.

• Review AI outputs related to sensitive subjects, including bias, misinformation, and harmful behaviors.

• Identify vulnerabilities overlooked by automated testing.

• Broaden evaluation coverage and minimize unexpected production issues.

• Collaborate on projects to train and enhance AI systems for Mercor’s AI lab and its enterprise clients.

⛳️ Requirements

• Native or fluent proficiency in both English and Kannada is essential.

• Strong judgment regarding language and content, particularly in assessing the accuracy, completeness, and appropriateness of AI responses.

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

• Keen attention to subtle errors, inconsistencies, and gaps.

• Capability to consistently adhere to taxonomies, benchmarks, playbooks, guidelines, and quality standards.

• Flexibility to adapt across different projects, task types, and clients.

• Must hold independent contractor status.

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

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

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

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

• Preferred: skills in psychology, acting, or writing that encourage unconventional adversarial thinking.

🏝️ Benefits

• Fully remote position that allows for flexible scheduling.

• Weekly payments through Stripe or Wise based on services provided.

• Opportunity to gain experience in human data-driven AI red teaming at the forefront of safety.

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

• Access to wellness resources and clear guidelines for projects involving higher sensitivity.

• Reasonable accommodations available upon request.

• Referral bonuses of up to $90 for each successful referral, subject to specific restrictions.