Вакансия из Hirify Global, списка международных tech-компаний Для мэтча и отклика нужен Plus
Пожаловаться
Зарплата и рынок
ЗП не указана
На похожих ролях по рынку
$170к$224кмедиана$308к
45 в выборке
На СНГ рынке: $3.9к/мес ($3.2к - $7.9к)
88
Хорошая вакансия
развернуть
У роли чёткая специализация на безопасности AI/ML и конкретные задачи по тестированию и защите систем; работа с федеральными заказчиками может зависеть от их требований.
Кликните для подробной информации
Работа на госзаказчикаУзкая AI-специализацияСильный соцпакетСовременный стек
Оценка от Hirify AI
Мэтч & Сопровод
Для мэтча с этой вакансией нужен Plus
Подключить Plus
Описание вакансии
Текст:
Hirify AI/Оригинал
TL;DR
AI/ML Security Specialist (R-00247) (AI/ML cybersecurity): Conducting security assessments, adversarial testing, and defensive engineering for AI/ML applications, models, training data, inference pipelines, and supporting infrastructure with an accent on vulnerability discovery, model attack evaluation, and federal security compliance. Focus on testing prompt injection, data poisoning, model extraction, model inversion, and evasion attacks, while developing threat models, remediation recommendations, and repeatable assessment methodologies.
Location: Hybrid in Ashburn, Virginia, United States
Company
hirify.global is a veteran-owned small business delivering cybersecurity and technology services to federal customers.
What you will do
Conduct OT&E and adversarial security assessments of AI/ML applications, models, training pipelines, inference systems, and supporting infrastructure.
Test for model evasion, adversarial manipulation, prompt injection, data poisoning, model extraction, model inversion, and AI-enabled attack paths.
Evaluate defenses and implement security controls to protect AI/ML systems and deployed applications.
Produce technical assessment reports covering methods, vulnerabilities, severity, and remediation recommendations.
Collaborate with cybersecurity engineers, AI/ML developers, technical leads, and federal stakeholders while aligning work with DHS, CBP, NIST, and applicable federal standards.
Requirements
Experience in cybersecurity engineering, security assessments, or penetration testing focused on AI/ML security, adversarial machine learning, and model evaluation.
Strong understanding of AI/ML architectures, machine learning algorithms, LLMs, model training pipelines, and secure deployment practices.
Hands-on experience evaluating AI-specific vulnerabilities and conducting penetration testing, vulnerability assessments, red teaming, or OT&E.
Proficiency with Python and familiarity with PyTorch, TensorFlow, or scikit-learn, plus security testing tools and adversarial assessment methodologies.
Knowledge of NIST AI RMF, NIST SP 800-53, the NIST Cybersecurity Framework, and applicable DHS/CBP security policies.
Strong analytical, problem-solving, written, and verbal communication skills, including the ability to present complex findings to federal stakeholders, engineering teams, and technical leadership.
Culture & Benefits
Full-time hybrid employment with competitive salary paid twice monthly.
Best-in-class medical coverage with 100% of medical premiums covered by True Zero.
Three weeks of PTO from start, 11 paid holidays, and parental leave.
401(k) program with a 100% company match on the first 4%.
Monthly reimbursement for cell phone and home internet costs.
Training and certification investment, plus business and contribution incentive programs.
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 →