Назад
Company hidden
4 дня назад

Red Team - Security Researcher III (AI Security)

Тип работы
fulltime
Грейд
senior
Английский
b2
Страна
Poland
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
Red Team - Security Researcher III (AI Security): Conducting advanced adversary emulation and offensive security research against internet-facing traffic management, security platforms, AI/ML implementations, and mission-critical APIs with an accent on LLM penetration testing, exploit development, and vulnerability research. Focus on designing objective-based red team operations, bypassing modern security controls, analyzing AI pipelines, and translating zero-day findings into architectural improvements and strategic risk assessments.

Location: Warsaw, Poland

Company

hirify.global develops solutions that help organizations create, secure, and run applications, with a focus on cybersecurity and digital infrastructure.

What you will do

  • Lead objective-based Red Team operations against global infrastructure, products, and AI/ML deployments.
  • Conduct AI and LLM penetration testing, including prompt injection, model inversion, data poisoning, and adversarial machine learning evasion.
  • Develop custom exploits, command-and-control infrastructure, and offensive tooling to bypass EDR, WAF, and XDR controls.
  • Research vulnerabilities across enterprise environments, MLOps pipelines, vector databases, and model hosting platforms.
  • Partner with Engineering and Blue Teams to turn offensive findings into architectural security improvements.
  • Publish security research, disclose zero-days, present at security conferences, and mentor engineering and security teams.

Requirements

  • 5–8+ years of hands-on offensive cybersecurity experience in Red Teaming, advanced penetration testing, or vulnerability research.
  • Experience with AI/ML security testing, the OWASP Top 10 for LLMs, and adversarial ML frameworks such as MITRE ATLAS.
  • Strong programming or scripting skills in Python, Go, C++, or Rust for custom tooling and exploit modification.
  • Deep knowledge of attacker tradecraft, including persistence, evasion, memory injection, and lateral movement across on-premises and AWS/Azure environments.
  • Familiarity with PyTorch, TensorFlow, Hugging Face, and enterprise AI deployment architectures.
  • Ability to explain exploit chains and zero-day research through strategic risk assessments for executive leadership.

Nice to have

  • Published security research, CVEs, successful bug bounties, or conference presentations, particularly in AI security or novel exploitation.
  • Offensive security certifications such as OSCP, OSEP, CRTO, CRTE, or OSWE.
  • Experience compromising major cloud environments, SaaS platforms, and MLOps pipelines.

Culture & Benefits

  • Work within the Office of the CISO as a specialized offensive security expert.
  • Collaborate directly with Engineering and Blue Teams on security architecture.
  • Contribute to the broader security community through research, disclosures, and conference presentations.
  • hirify.global promotes equal employment opportunities and provides reasonable accommodations during the application process.

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 →