GenAI Safety Team Lead
Core
Lead a multidisciplinary team in adversarial testing, risk evaluations, and data-driven analyses to identify and mitigate risks in Generative AI systems.
Role type
Senior IC GenAI Safety Team Lead (Red Teaming)
Builds
AI safety reports, adversarial datasets, and risk mitigation strategies for model hardening and runtime guardrails.
Domain
Generative AI safety, Responsible AI, and machine learning security.
Deliverable
production ML models
Required skills
Red teaming, adversarial testing, model evaluation, project management, client communication, strategic thinking, data analysis, risk assessment, team leadership.
Preferred skills
AI safety research, publication authoring, evaluation framework development, mentorship, industry conference participation.
Technologies
Generative AI models, multimodal systems, benchmarking tools, adversarial datasets.
Responsibilities
Design and refine red teaming methodologies for Responsible AI projects; guide development of adversarial testing strategies for text, image, and multimodal systems; oversee production of datasets, reports, and analyses; review and approve deliverables for quality and ethical standards; attend client meetings to address methodological questions.
Seniority
Senior, hands-on IC with operational leadership
