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

📋 Description

• Engage in red-team activities for conversational AI models and agents, focusing on jailbreaks, prompt injections, misuse scenarios, bias exploitation, and multi-turn manipulations.

• Document failures, categorize vulnerabilities, and identify systemic risks.

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

• Generate reproducible reports, datasets, and attack scenarios.

• Review AI outputs related to sensitive issues such as bias, misinformation, and harmful behaviors.

• Increase evaluation breadth and reveal vulnerabilities that automated testing might overlook.

• Collaborate on initiatives aimed at training and improving frontier AI systems for Mercor's clientele.

⛳️ Requirements

• Required fluency/native proficiency in English and Marathi.

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

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

• Consistent adherence to guidelines and quality standards.

• Capability to communicate reasoning effectively to both technical and non-technical audiences.

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

• Independent contractor status is required.

• Candidates must not hold H-1B or STEM OPT status.

• Preferred qualifications include expertise in adversarial ML, cybersecurity, socio-technical risk, or creative probing.