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 jailbreaks, prompt injections, misuse scenarios, bias exploitation, and multi-turn manipulations.

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

• Implement taxonomies, benchmarks, and playbooks to maintain testing consistency.

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

• Identify vulnerabilities that automated testing may overlook.

• Broaden evaluation coverage and minimize unexpected issues in production.

• Assist Mercor’s AI-lab and corporate clients in enhancing the safety, robustness, and trustworthiness of frontier AI systems.

⛳️ Requirements

• Native proficiency in both English and Bengali.

• 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 push them to their limits.

• Familiarity with using frameworks, taxonomies, benchmarks, or structured playbooks.

• Ability to articulate risks clearly to both technical and non-technical audiences.

• Flexibility to adapt across different projects and client needs.

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

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

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

• Preferred: background in psychology, acting, or writing to encourage unconventional adversarial thinking.

• Must meet eligibility criteria; H-1B and STEM OPT candidates are not eligible.

• Engagement as an independent contractor.

🏝️ Benefits

• Fully remote position.

• Flexible working hours / ability to work according to your own schedule.

• Weekly payments via Stripe or Wise.

• Project durations may be extended, reduced, or concluded prematurely based on needs and performance.

• Participation in higher-sensitivity projects is optional.

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

• Reasonable accommodations provided upon request.

• Competitive compensation.

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