Вакансия из Hirify Global, списка международных tech-компаний Для мэтча и отклика нужен Plus
Пожаловаться
Зарплата и рынок
Нижеразвернуть
$125к-160к/год
$170к$200кмедиана$220к
По похожим ролям (50) ~ $200к/год
На СНГ рынке: $4.3к/мес ($3.6к - $5.1к)
74
Хорошая вакансия
развернуть
Роль описана достаточно четко и включает серьезную практическую работу по безопасности ИИ, но охватывает сразу технический редтиминг, исследования, руководство командой и поддержку корпоративной безопасности.
Ниже рынка
?Широкий круг задач
Актуальная специализация
Влияние на здравоохранение
Мэтч & Сопровод
Для мэтча с этой вакансией нужен Plus
Подключить Plus
Описание вакансии
Текст:
Hirify AI/Оригинал
TL;DR
Senior Red Team AI Security Engineer (AI Security): Testing and strengthening generative AI, computer vision, and natural language processing systems against prompt injection, data poisoning, model inversion, evasion, and jailbreak attacks with an accent on adversarial machine learning, ethical AI risks, and automated security assessment. Focus on developing offensive AI tools, executing full-lifecycle red team operations, validating blue-team detections, and researching emerging threats to AI systems.
Location: Schrafft City Center, United States of America
Annual base salary: $125,000–$160,000 USD
Company
hirify.global is a healthcare organization with more than 35,000 employees serving patients and communities.
What you will do
Lead and execute red team operations against AI/ML systems, including prompt injection, data poisoning, model inversion, evasion, and jailbreak simulations.
Assess generative AI, computer vision, and natural language processing systems for vulnerabilities, bias, fairness issues, harmful content, and responsible AI compliance risks.
Develop custom exploits, adversarial input-generation infrastructure, automated testing frameworks, and privacy-preserving attacks for federated learning environments.
Research emerging AI threats and offensive AI techniques, publish findings, and integrate AI/ML tools into threat simulation and anomaly detection.
Plan and coordinate full-lifecycle red team engagements, including reconnaissance, command and control setup, lateral movement, and adversary emulation.
Mentor junior engineers, lead small engagement teams, collaborate with AI, blue, purple, trust and safety, and incident response teams, and provide actionable defensive recommendations.
Requirements
3–5+ years of experience in offensive security, penetration testing, or red teaming, including 1–2+ years of hands-on experience with AI/ML systems and frameworks.
Expertise with red teaming tools such as Kali Linux, Metasploit, Wireshark, and Burp Suite.
Ability to apply traditional penetration testing and red team methodologies.
Knowledge of machine learning fundamentals and model architectures.
Ability to evaluate model performance under adversarial conditions and communicate actionable security recommendations.
BS preferred.
Preferred certifications include Certified Ethical Hacker, OSCP, OSEP, similar offensive security certifications, or AI/ML security certifications.
Nice to have
Experience with AI model interpretability and automation tools.
Culture & Benefits
Full-time employment in a healthcare organization focused on protecting patients, colleagues, and communities.
All staff must be vaccinated against influenza as a condition of employment.
Equal opportunity employer committed to veterans and people 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 →