AI Safety Expert – English, Bengali

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

📋 Description

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

• Create human data through the annotation of failures, classification of vulnerabilities, and identification of systemic risks.

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

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

• Analyze AI outputs related to sensitive subjects such as bias, misinformation, or harmful behaviors.

• Identify vulnerabilities that automated testing may overlook.

• Broaden evaluation coverage and minimize unexpected issues in production.

• Enhance customer AI systems through adversarial testing methodologies.

⛳️ Requirements

• Native or fluent proficiency in both English and Bengali is mandatory.

• Previous experience in red teaming, particularly in AI adversarial contexts, cybersecurity, or socio-technical investigations.

• Capability to probe AI systems adversarially and test their limits.

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

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

• Flexibility to adapt across various projects and clients.

• Preferred expertise includes adversarial machine learning, jailbreak datasets, prompt injection, RLHF/DPO attacks, model extraction, penetration testing, exploit development, reverse engineering, harassment/disinformation probing, abuse analysis, conversational AI testing, psychology, acting, or writing.

• Must hold independent contractor status.

• Candidates on H1-B or STEM OPT visas will not be considered.

🏝️ Benefits

• Enjoy the flexibility of fully remote work on your own schedule.

• Receive weekly payments through Stripe or Wise.

• Optional participation in projects with higher sensitivity levels.

• Access to clear content guidelines prior to engaging with sensitive subjects.

• Benefit from wellness resources.

• Competitive compensation package.

• Earn referral payments of up to $90 for each successful referral.

• Collaborate with leading researchers in the field.

• Reasonable accommodations available upon request.