AI Safety Expert – English, Bengali

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

📋 Description

• Conduct red-team evaluations of 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, classifying vulnerabilities, and identifying systemic risks.

• Utilize taxonomies, benchmarks, and playbooks to ensure consistent testing procedures.

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

• Assess AI outputs related to sensitive subjects, including 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 the development of reproducible artifacts.

• Collaborate with top researchers on projects aimed at training and improving cutting-edge AI systems.

⛳️ Requirements

• Proficient/native fluency in both English and Bengali is mandatory.

• Strong evaluative skills regarding language and content.

• Capability to determine whether AI responses are accurate, comprehensive, and suitable, and articulate the reasoning behind these assessments.

• Attention to detail in spotting subtle errors, inconsistencies, and omissions.

• Consistent adherence to guidelines and quality standards.

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

• Flexibility to adapt across various projects, tasks, and clients.

• Status as an independent contractor.

• Not eligible if an H1-B or STEM OPT candidate.

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

• Preferred: background in cybersecurity, encompassing penetration testing, exploit development, or reverse engineering.

• Preferred: experience with socio-technical risks, such as harassment/disinformation probing, abuse analysis, or conversational AI testing.

• Preferred: experience in psychology, acting, or writing for unconventional adversarial thinking.

🏝️ Benefits

• Fully remote position.

• Flexible work schedule allowing you to set your own hours.

• Weekly compensation via Stripe or Wise.

• Access to wellness resources and clear guidelines for higher-sensitivity projects.

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

• Chance to contribute to the development of more robust, safe, and trustworthy AI systems.

• Competitive compensation.

• Collaboration with leading researchers in the field.

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