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 through methods such as jailbreaks, prompt injections, misuse scenarios, bias exploitation, and multi-turn manipulations.

• Generate human data by annotating errors, classifying vulnerabilities, and identifying systemic risks.

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

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

• Evaluate AI outputs concerning sensitive subjects like bias, misinformation, and harmful behaviors.

• Assist in broadening evaluation coverage and enhancing client AI systems.

⛳️ Requirements

• Proficient/native proficiency in English and Bengali.

• Strong judgment regarding language and content; capable of assessing the accuracy, completeness, and appropriateness of AI responses and articulating the reasoning behind evaluations.

• Keen ability to detect subtle errors, inconsistencies, and omissions.

• Consistently adhere to guidelines and quality standards.

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

• Flexibility across various projects, task types, and clients.

• Must operate as an independent contractor.

• Must not require H1-B or STEM OPT sponsorship.

• Preferred: experience in adversarial machine learning, including jailbreak datasets, prompt injection, RLHF/DPO attacks, or model extraction.

• Preferred: experience in cybersecurity, such as penetration testing, exploit development, or reverse engineering.

• Preferred: experience in socio-technical risk analysis, including harassment/disinformation probing, abuse analysis, or conversational AI testing.

• Preferred: background in psychology, acting, or writing for unconventional adversarial thought processes.

🏝️ Benefits

• Fully remote position.

• Flexible working hours to manage your schedule.

• Weekly payments through Stripe or Wise.

• Optional participation in higher-sensitivity projects.

• Clear guidelines and wellness resources available for sensitive-content tasks.

• Competitive compensation.

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

• Collaborate with leading experts in the field.

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