Назад
Company hidden
12 дней назад

AI Security Engineer

115 600 - 158 900$
Формат работы
hybrid
Тип работы
fulltime
Грейд
senior
Английский
b2
Страна
US
Вакансия из списка Hirify.GlobalВакансия из Hirify Global, списка международных tech-компаний
Для мэтча и отклика нужен Plus

Мэтч & Сопровод

Для мэтча с этой вакансией нужен Plus

Описание вакансии

Текст:
/
TL;DR
AI Security Engineer (AI Security/Agentic AI): Securing enterprise AI agents, models, tool integrations, and retrieval pipelines with an accent on adversarial testing, automated guardrails, and AI governance. Focus on designing prompt-injection and data-leakage attack scenarios, controlling agent permissions and vector-store access, and building secure-by-default architectures for production AI systems.

Location: Hybrid in Westminster, Colorado, United States; 10% travel required

Salary: $115,600–$158,900 per year

Company

hirify.global is an industrial technology company creating solutions that connect the digital and physical worlds across construction, geospatial, transportation, government, and related industries.

What you will do

  • Assess and secure AI agents, tool integrations, agentic workflows, permission scopes, action chains, and non-human identity frameworks.
  • Design and execute adversarial attack scenarios involving prompt injection, jailbreaking, insecure output handling, and data leakage in retrieval pipelines.
  • Partner with AI engineers to implement automated security guardrails, vector-store access controls, and output-filtering policies across model lifecycles.
  • Audit AI operations pipelines, assess third-party AI supply-chain components, and lead model risk assessments before production deployment.
  • Develop enterprise AI security standards and train AppSec, SecOps, and GRC teams on AI attack classes and mitigations.

Requirements

  • 5+ years of security engineering or application security experience with technical depth in AI attack classes.
  • Hands-on proficiency with Python, MLOps tooling, PyTorch, TensorFlow, and MCP agent protocols.
  • Practical AI red-teaming experience with tools such as PyRIT, Garak, or Promptfoo.
  • Experience with cloud security architecture across AWS, Azure, or GCP and containerized environments.
  • Knowledge of OWASP Top 10 for LLMs, OWASP agentic threat guidance, and NIST AI RMF standards.

Nice to have

  • Experience with commercial AI security platforms, shadow AI discovery tools, or MITRE ATLAS tactics.
  • Awareness of ISO/IEC 42001 and the EU AI Act.
  • Open-source AI security contributions, published research, CVEs, or conference speaking experience.
  • Certifications such as OSCP, OSCE, AWS Security Specialty, or GIAC cloud security certifications.

Culture & Benefits

  • Purpose-driven work focused on improving productivity, safety, and sustainability in essential industries.
  • Collaborative and supportive environment built around belonging, innovation, ownership, and practical execution.
  • Medical, dental, vision, life, disability, time-off, and retirement plans.
  • Additional benefits may include tax savings plans, paid parental leave, and an employee stock purchase plan.
  • Bonus eligibility is available; the role is not commission-eligible.

Hiring process

  • Submit an online application; applications are accepted until the position is filled.

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 →