AI Safety Expert - Bilingual
Summary
Remote contract role for bilingual (English/Malayalam) AI safety experts who red-team conversational AI models and agents — probing for jailbreaks, prompt injections, misuse, and bias — then annotate failures and produce reports and datasets for AI research labs. Adversarial ML or cybersecurity background preferred.
About the job
Mercor connects elite creative and technical talent with leading AI research labs. Headquartered in San Francisco, our investors include Benchmark, General Catalyst, Peter Thiel, Adam D'Angelo, Larry Summers, and Jack Dorsey.
Position: AI Safety Experts — English & Malayalam
Type: Contract
Compensation: $16–$22/hour
Location: Remote
Role Responsibilities
- Red team conversational AI models and agents. Focus on jailbreaks, prompt injections, misuse cases, and bias exploitation.
- Generate high-quality human data. Annotate failures, classify vulnerabilities, and flag systemic risks.
- Apply structure by following taxonomies, benchmarks, and playbooks to maintain consistent testing.
- Document reproducibly. Produce reports, datasets, and attack cases that customers can act on.
- Review AI outputs on sensitive topics like bias, misinformation, or harmful behaviors. Participation in higher-sensitivity projects is optional and supported by guidelines and wellness resources.
Qualifications
Must-Have
- Native fluency in English and Malayalam.
- Strong judgment about language and content. Ability to assess AI response accuracy, completeness, and appropriateness.
- Rigorous attention to detail. Notice subtle errors, inconsistencies, and gaps.
- Structured approach. Adhere to guidelines and quality standards consistently.
- Strong communication skills. Explain reasoning clearly to technical and non-technical audiences.
- Adaptability. Thrive across projects, task types, and customers.
Preferred
- Knowledge in Adversarial ML: jailbreak datasets, prompt injection, RLHF/DPO attacks, model extraction.
- Experience in Cybersecurity: penetration testing, exploit development, reverse engineering.
- Understanding of socio-technical risk: harassment/disinfo probing, abuse analysis, conversational AI testing.
- Skills in creative probing: psychology, acting, writing for unconventional adversarial thinking.
Application Process (Takes 20–30 mins to complete)
- Upload resume
- AI interview based on your resume
- Submit form
Resources & Support
- For details about the interview process and platform information, please check: https://talent.docs.mercor.com/welcome
- For any help or support, reach out to: support@mercor.com
PS: Our team reviews applications daily. Please complete your AI interview and application steps to be considered for this opportunity.