Hazardous Device Red Team Specialist for AI Safety

Mercor

United States

À distance

USD 90 000 - 140 000

Plein temps

14 jours+

Obtenez une réponse de cet employeur

Votre CV et votre lettre de motivation, adaptés exactement à ce que l’employeur recherche.

Passez les filtres ATS

Résumé du poste

Mercor is assembling a panel of energetic materials and propulsion experts to red-team frontier AI models, testing whether a model can fully answer legitimate questions while refusing dangerous ones. You will write prompts at three levels and assess model outputs against policy standards.

This role emphasizes clear, written rationale for judgments and the development of reference answers with detailed reasoning.

Qualifications

  • Public safety professional with real-device assessment experience.
  • Ability to distinguish routine questions from sensitive ones with a clear written rationale.
  • Experience in evaluating model responses against policy standards.

Responsabilités

  • Write challenging single-turn prompts at benign, dual-use, and adversarial levels.
  • Evaluate model responses against a defined policy standard.
  • Write the reference answer and technical reasoning for correct responses.

Connaissances

Public safety background
Red-teaming experience
Written communication

Description du poste

Mercor is assembling a panel of energetic materials and propulsion experts to red-team frontier AI models, testing whether a model can fully answer legitimate questions while refusing dangerous ones. You will write prompts at three levels and assess model outputs against policy standards.

This role emphasizes clear, written rationale for judgments and the development of reference answers with detailed reasoning.

Obtenez votre examen gratuit et confidentiel de votre CV.

ou faites glisser et déposez votre fichier ici.

Similar jobs

Postes similaires à comparer

Public Safety Red Team Specialist
Public Safety Red Team Specialist

Mercor • San Francisco (CA)

À distance
USD 120 000 - 180 000
Chemical Safety Red Team Specialist for AI Risk
Chemical Safety Red Team Specialist for AI Risk

Mercor • New York (NY)

À distance
USD 90 000 - 140 000
Propulsion Systems Engineer - AI Safety Red Team
Propulsion Systems Engineer - AI Safety Red Team

Mercor • San Francisco (CA)

Sur place
USD 140 000 - 180 000
AI Safety Chemist — Hazardous Chemistry Red-Teaming
AI Safety Chemist — Hazardous Chemistry Red-Teaming

Mercor • San Francisco (CA)

À distance
USD 120 000 - 190 000
Propulsion Safety & AI Red-Team Engineer
Propulsion Safety & AI Red-Team Engineer

Mercor • San Francisco (CA)

À distance
USD 120 000 - 180 000
Analytical Chemist — AI Safety Red Team & Hazards
Analytical Chemist — AI Safety Red Team & Hazards

Mercor • États-Unis

À distance
USD 90 000 - 130 000
Industrial Hygienist: AI Safety Red-Team Evaluator
Industrial Hygienist: AI Safety Red-Team Evaluator

Mercor • San Francisco (CA)

Sur place
USD 120 000 - 180 000
Blasting Engineer - AI Safety Red-Teaming Prompt Lead
Blasting Engineer - AI Safety Red-Teaming Prompt Lead

Neon • États-Unis

À distance
USD 70 000 - 120 000
Radiological Safety Red-Teamer for AI Risk Evaluation
Radiological Safety Red-Teamer for AI Risk Evaluation

Mercor • États-Unis

À distance
USD 100 000 - 140 000
Blasting Specialist: AI Safety Red-Teaming & Prompt Design
Blasting Specialist: AI Safety Red-Teaming & Prompt Design

Mercor • San Francisco (CA)

À distance
USD 95 000 - 140 000