Чётко очерченная роль в red team крупной AI-компании даёт возможность работать над реальной безопасностью ИИ, но предполагает регулярное присутствие в офисе.
Безопасность ИИ
Понятные задачи
Сильный бренд
?Офис 3 дня
Мэтч & Сопровод
Для мэтча с этой вакансией нужен Plus
Подключить Plus
Описание вакансии
Текст:
Hirify AI/Оригинал
TL;DR
Novel Abuse Red Teamer (AI): Designing and executing adversarial attack simulations and application security testing to uncover novel abuse vectors in AI models and products with an accent on web application security, threat actor emulation, and detection improvements. Focus on developing testing automation, translating technical findings into actionable defenses, and coordinating security, product, and policy responses to emerging threats.
Location: San Francisco, CA; other locations include Seattle and US Remote. Hybrid work model with 3 days in the office per week. Relocation assistance is offered to new employees.
Salary: $158.4K–$320K plus equity.
Company
OpenAI is an AI research and deployment company developing general-purpose AI systems and products with a focus on safe and responsible deployment.
What you will do
Design and execute realistic attack simulations that emulate sophisticated threat actor methodologies.
Perform adversarial testing and application security assessments to uncover novel abuse and exploitation vectors in web applications, AI systems, and unique attack surfaces.
Analyze testing outcomes and produce actionable insights to improve detection mechanisms and overall product defenses.
Connect security, product, and policy teams so adversarial testing informs defense strategies and remediation.
Develop and integrate automation tools to streamline testing workflows and support rapid iteration against emerging threats.
Collaborate with internal stakeholders to align testing strategies with product needs and security objectives.
Requirements
Experience in application security, penetration testing, or red team operations, with a proven record of executing adversarial testing and simulation protocols.
Strong technical background in web application security and hands-on experience testing web applications, AI systems, and unique attack surfaces.
Hands-on proficiency with tools such as Burp Suite, Metasploit, and similar tools.
Attacker mindset and ability to identify novel abuse vectors in live environments.
Ability to translate complex technical findings into actionable insights.
Demonstrated success working cross-functionally in fast-paced environments, managing complex product ecosystems, and driving rapid security improvements.
Commitment to continuous learning, innovation, and advanced security methodologies for protecting AI technologies.
Culture & Benefits
Work with cross-functional security, product, policy, and engineering partners.
Hybrid work arrangement with three office days per week.
Relocation assistance for new employees.
Equity included in the compensation package.
OpenAI is an equal opportunity employer and provides reasonable accommodations for applicants with disabilities.
Будьте осторожны
Если работодатель просит войти в их систему, используя iCloud/Google, прислать код/пароль, запустить код/ПО, не делайте этого. Это мошенники. Обязательно жмите «Пожаловаться» или пишите в поддержку. Подробнее в гайде →