Frontier AI Safety Red Team Specialist
Enregistrez cette offre et organisez votre recherche
Créez un compte gratuit pour enregistrer des offres d'emploi, créer des alertes et revenir à cette liste depuis votre tableau de bord.
Mercor is seeking experienced AI Safety Red Teamers to identify vulnerabilities in frontier AI systems through adversarial testing. You will design challenging prompts, uncover model weaknesses, and evaluate AI behavior across complex, high-risk topics.
Responsibilities include designing adversarial prompts, identifying jailbreaks and policy failures, and evaluating model robustness across sensitive domains.
-
Frontier AI Safety Red Team Specialist
Il y a 11 heures
Brussel Hoofdstad, Brussel Hoofdstad, Belgique Obsidian Télétravail Temps plein 90 000 € - 130 000 € ContratObsidian in Belgium seeks experienced AI Safety Red Teamers to identify vulnerabilities in frontier AI systems through adversarial testing.You will design challenging prompts, uncover jailbreaks, unsafe behaviours, and policy failures, and document findings for safety benchmarking and red-teaming reports.Collaborate with researchers to improve alignment,...
-
Frontier AI Safety Red Team Lead
Il y a 11 heures
Brussel Hoofdstad, Brussel Hoofdstad, Belgique Mercor Temps plein 90 000 € - 130 000 € ContratMercor is seeking experienced AI Safety Red Teamers to identify vulnerabilities in frontier AI systems through adversarial testing. You will design challenging prompts and evaluate model behavior across high-risk topics.Responsibilities include stress-testing models, uncovering jailbreaks and policy failures, and documenting vulnerabilities for safety...
-
Remote AI Safety Red Team Specialist
Il y a 11 heures
Brussel Hoofdstad, Brussel Hoofdstad, Belgique Mercor Temps plein 78 000 € - 104 000 € ContratMercor is assembling a remote red team for AI safety, focusing on adversarial data curation and vulnerability assessment. The role involves testing AI models with jailbreaks, prompt injections, and misuses, while generating high-quality datasets and reproducible reports for customers.You will operate with a structured framework, documenting findings and...
-
AI Safety Red Teamer Expert
Il y a 11 heures
Brussel Hoofdstad, Brussel Hoofdstad, Belgique Mercor Temps plein 90 000 € - 130 000 € ContratWe are seeking experienced AI Safety Red Teamers to identify vulnerabilities in frontier AI systems through adversarial testing. You will design challenging prompts, uncover model weaknesses, and evaluate AI behavior across complex, high-risk, and ambiguous ("grey-area") topics.ResponsibilitiesDesign adversarial prompts to stress-test frontier AI...
