A
GenAI Safety Team Lead
Activefence
New York, NY, US
🏢 Офис
Senior
Полная занятость
Продуктовая
Tech
Описание вакансии
Обязанности
•Attend client meetings on methodology
•Collaborate with cross-department teams
•Conduct data-driven risk analysis
•Design red teaming methodologies
•Develop adversarial testing strategies
•Evaluate generative AI model risks
•Oversee red teaming dataset production
•Present deliverables to clients
•Review and approve AI safety deliverables
•Support emerging AI risk research
Технологии: AI Safety, Adversarial Testing, Benchmarking, Client Communication, Data Analysis, Ethical Standards, Evaluation Frameworks, Evaluation datasets, Model Evaluation, Multimodal Systems, Red Teaming, Responsible AI, Risk Assessment