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

📋 Description

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

• Create human data by annotating failures, identifying vulnerabilities, and flagging systemic risks.

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

• Generate reproducible reports, datasets, and attack scenarios.

• Examine AI outputs related to sensitive subjects like bias, misinformation, and harmful behaviors.

• Identify vulnerabilities overlooked by automated testing.

• Broaden evaluation coverage and minimize unforeseen issues in production.

• Enhance customer AI systems through adversarial testing.

⛳️ Requirements

• Proficient fluency in both English and Odia is essential.

• Strong discernment regarding language and content; capability to evaluate if AI responses are accurate, complete, and suitable, along with the ability to justify assessments.

• Keen attention to detail for noticing subtle errors, inconsistencies, and gaps.

• Consistent adherence to guidelines and quality standards.

• Clear communication of reasoning to both technical and non-technical audiences.

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

• Engagement as an independent contractor.

• Candidates must not be on an H-1B or STEM OPT visa.

• Preferred qualifications include expertise in adversarial machine learning, cybersecurity, socio-technical risk, and creative probing.