AI Safety Specialist - Fully Remote | Upto $22/hr

Résumé du poste

Red team conversational AI models to identify vulnerabilities like jailbreaks and prompt injections. Generate high-quality human data by annotating failures and documenting findings to improve model performance.

Détails du poste

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 & Assamese Type: Contract Compensation: $20–$22/hour Location: Remote Role Responsibilities Red team conversational AI models and agents to identify vulnerabilities such as jailbreaks, prompt injections, and misuse cases. Generate high-quality human data by annotating failures, classifying vulnerabilities, and flagging systemic risks. Apply structure using taxonomies, benchmarks, and playbooks to ensure consistent testing. Document findings reproducibly to create reports, datasets, and attack cases for customer action. Work independently and asynchronously to meet deadlines while improving AI model performance. Qualifications Must-Have Fluent in English and Assamese. Prior experience in red teaming, AI adversarial work, or cybersecurity. Strong communication skills to explain risks to both technical and non-technical stakeholders. Preferred Experience with adversarial ML, cybersecurity, and socio-technical risk analysis. Skills in creative probing such as psychology, acting, or 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.

Ce que vous ferez

Red team conversational AI models to identify vulnerabilities like jailbreaks and prompt injections. Generate high-quality human data by annotating failures and documenting findings to improve model performance.

Exigences

Must be fluent in English and Assamese with prior experience in red teaming, AI adversarial work, or cybersecurity. Strong communication skills and experience with adversarial ML or socio-technical risk analysis are preferred.

Compétences indiquées

• Technical · Souhaitée
• analysis · Souhaitée
• safety · Souhaitée
• Process · Souhaitée
• Communication · Souhaitée
• meet deadlines · Souhaitée
• Communication Skills · Souhaitée
• Consistent · Souhaitée
• Strong communication skills · Souhaitée
• Strong Communication · Souhaitée
• Customer · Souhaitée
• Anglais · Souhaitée

Autres compétences pertinentes

Relevées dans la description du poste. Confirmez les exigences importantes ci-dessus.

• Red Teaming
• AI Adversarial Work
• Cybersecurity
• English Fluency
• Assamese Fluency
• Adversarial ML
• Socio-technical Risk Analysis
• Prompt Injection Identification
• Data Annotation
• Vulnerability Classification

Domaines d’emploi

• Security & Safety
• Software
• Technology
• Data & Analytics
• Science & Research