AI Safety Experts – English, Punjabi

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

📋 Description

• Conduct red-team assessments on conversational AI models and agents by exploiting jailbreaks, prompt injections, misuse scenarios, bias vulnerabilities, and multi-turn manipulations.

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

• Utilize taxonomies, benchmarks, and playbooks to ensure uniform testing processes.

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

• Identify vulnerabilities that automated tests may overlook.

• Broaden evaluation coverage and minimize unexpected issues in production.

• Enhance customer AI systems, boosting their safety, robustness, and trustworthiness.

⛳️ Requirements

• Proficient/native fluency in English and Punjabi.

• Previous experience in red teaming related to AI adversarial work, cybersecurity, or socio-technical probing.

• Capability to probe AI systems in an adversarial manner and test their limits.

• Familiarity with frameworks, taxonomies, benchmarks, or playbooks for systematic testing.

• Skill in clearly communicating risks to both technical and non-technical audiences.

• Flexibility to adapt across various projects and clients.

• Preferred expertise includes adversarial machine learning, cybersecurity, socio-technical risk, or innovative probing methods.

• Currently unable to accommodate H1-B or STEM OPT candidates.

• Must operate as an independent contractor.

🏝️ Benefits

• Fully remote position.

• Flexible work hours / freedom to create your own schedule.

• Weekly payments processed through Stripe or Wise.

• Voluntary participation in projects with higher sensitivity.

• Clear guidelines and wellness resources available for projects involving sensitive content.

• Competitive compensation.

• Opportunity to collaborate with leading researchers.

• Referral bonus of up to $90 for each successful referral.