Remote AI Safety Red Team Engineer

Mercor

Belgique

Sur place

EUR 90 000 - 150 000

Plein temps

14 jours+
Générateur de candidature

Démarquez-vous pour ce poste — générez un CV et une lettre de motivation personnalisés en environ une minute.

Passez les filtres ATS

Résumé du poste

Mercor is assembling a red team for this project - human data experts who probe AI models with adversarial inputs, surface vulnerabilities, and generate the red team data that makes AI safer for our customers. This project involves reviewing AI outputs that touch on sensitive topics such as bias, misinformation, or harmful behaviors.

All work is text-based, and participation in higher-sensitivity projects is optional and supported by clear guidelines and wellness resources.

Qualifications

  • Prior red-teaming experience (AI adversarial work, cybersecurity, socio-technical probing).
  • Curious and adversarial: you instinctively push systems to breaking points.
  • Structured: you use frameworks or benchmarks, not just random hacks.
  • Communicative: you explain risks clearly to technical and non-technical stakeholders.
  • Adaptable: thrive on moving across projects and customers.

Responsabilités

  • Red team conversational AI models and agents: jailbreaks, prompt injections, misuse cases, bias exploitation, multi-turn manipulation
  • Generate high-quality human data: annotate failures, classify vulnerabilities, and flag systemic risks
  • Apply structure: follow taxonomies, benchmarks, and playbooks to keep testing consistent
  • Document reproducibly: produce reports, datasets, and attack cases customers can act on

Connaissances

Red Teaming
Adversarial AI
Cybersecurity
Socio-technical probing
Structured thinking
Communication
Adaptability

Description du poste

Mercor is assembling a red team for this project - human data experts who probe AI models with adversarial inputs, surface vulnerabilities, and generate the red team data that makes AI safer for our customers. This project involves reviewing AI outputs that touch on sensitive topics such as bias, misinformation, or harmful behaviors.

All work is text-based, and participation in higher-sensitivity projects is optional and supported by clear guidelines and wellness resources.

Obtenez votre examen gratuit et confidentiel de votre CV.
ou faites glisser et déposez votre fichier ici.
Similar jobs

Postes similaires à comparer

Remote AI Safety Red Team Specialist
Remote AI Safety Red Team Specialist

Mercor • Brussel Hoofdstad

Sur place
EUR 77 000 - 112 000
Remote AI Safety Red Team Specialist
Remote AI Safety Red Team Specialist

Mercor • Brussel Hoofdstad

Sur place
EUR 78 000 - 104 000
Remote AI Safety Red Team Specialist
Remote AI Safety Red Team Specialist

Mercor • Belgique

À distance
USD 90 000 - 150 000
Frontier AI Safety Red Team Lead
Frontier AI Safety Red Team Lead

Mercor • Brussel Hoofdstad

Sur place
EUR 90 000 - 130 000
AI Safety Specialist - Fully Remote
AI Safety Specialist - Fully Remote

Mercor • Belgique

À distance
USD 90 000 - 150 000
AI Safety Red Teamer Expert
AI Safety Red Teamer Expert

Mercor • Brussel Hoofdstad

Sur place
EUR 90 000 - 130 000
Frontier AI Safety Red Team Specialist
Frontier AI Safety Red Team Specialist

Obsidian • Brussel Hoofdstad

À distance
EUR 90 000 - 130 000
Frontier AI Safety Evaluator
Frontier AI Safety Evaluator

Mercor • Brussel Hoofdstad

À distance
EUR 70 000 - 110 000
Frontier AI Safety Evaluator & Alignment Specialist
Frontier AI Safety Evaluator & Alignment Specialist

Mercor • Brussel Hoofdstad

Sur place
EUR 70 000 - 110 000
Frontier AI Safety Evaluator: Expert Reviewer
Frontier AI Safety Evaluator: Expert Reviewer

Mercor • Brussel Hoofdstad

Sur place
EUR 70 000 - 110 000