AI Safety Expert, English – Punjabi

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

📋 Description

• Engage in red-teaming for conversational AI models and agents

• Assess vulnerabilities through jailbreaks, prompt injections, misuse cases, bias exploitation, and multi-turn manipulation

• Document AI failures and categorize vulnerabilities

• Identify and report systemic risks

• Utilize taxonomies, benchmarks, and playbooks to ensure consistent testing methodologies

• Generate reproducible reports, datasets, and attack scenarios

• Investigate AI systems for vulnerabilities that automated testing may overlook

• Enhance evaluation coverage and mitigate unexpected production issues

• Foster customer confidence in the safety of AI technologies

⛳️ Requirements

• Proficiency in both English and Punjabi is essential

• Previous experience in red teaming within AI adversarial contexts, cybersecurity, or socio-technical probing is necessary

• Capability to conduct adversarial probing of AI systems, covering jailbreaks, prompt injections, misuse cases, bias exploitation, and multi-turn manipulation

• Experience in producing human data through the annotation of failures, classification of vulnerabilities, and identification of systemic risks

• Competence in adhering to established taxonomies, benchmarks, and playbooks

• Ability to create reproducible reports, datasets, and attack scenarios

• Skill in articulating risks to both technical and non-technical audiences

• Flexibility to adapt across varying projects and client requirements

• Status as an independent contractor is required

• Candidates must not hold H1-B or STEM OPT status

🏝️ Benefits

• Position is fully remote

• Flexible working hours, allowing you to manage your own schedule

• Weekly payments facilitated through Stripe or Wise

• Project timelines may be adjusted based on needs and performance

• Access to wellness resources and clear protocols for sensitive projects

• Reasonable accommodations available upon request

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

• Opportunity to directly contribute to enhancing the robustness, safety, and trustworthiness of AI systems

• Competitive compensation

• Collaboration with leading researchers in the field