Назад
Company hidden
1 месяц назад

Sr. Red Team - Security Researcher (AI Security)

Формат работы
onsite
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
Sr. Red Team - Security Researcher (AI Security) (AI/LLM security): Conducting advanced red-team operations and evaluating the security of internet-facing infrastructure, security platforms, AI/ML deployments, and mission-critical APIs with an accent on prompt injection, model inversion, data poisoning, adversarial machine learning, and custom exploit development. Focus on researching vulnerabilities across MLOps pipelines, vector databases, cloud environments, and model-hosting platforms while translating exploit chains into strategic risk assessments and architectural hardening.

Location: Warsaw, Poland

Company

hirify.global develops cybersecurity, traffic management, and application security solutions, including platforms that help organizations create, secure, and run applications.

What you will do

  • Lead complex, objective-based red-team operations against global infrastructure, products, and AI/ML deployments.
  • Conduct AI and LLM penetration testing covering prompt injection, model inversion, data poisoning, and adversarial machine learning evasion techniques.
  • Research and develop custom exploits, command-and-control infrastructure, and offensive tooling to bypass EDR, WAF, and XDR controls.
  • Perform vulnerability research across enterprise environments, MLOps pipelines, vector databases, model-hosting platforms, and cloud systems.
  • Partner with Engineering and Blue Teams to convert offensive findings into architectural improvements and stronger systems.
  • Publish research, disclose zero-days, present at security conferences, and mentor engineering and security teams on AI-driven attacks.

Requirements

  • 5–8+ years of hands-on experience in offensive cybersecurity, including red teaming, advanced penetration testing, or vulnerability research.
  • Demonstrated experience in AI/ML security testing, including deep knowledge of the OWASP Top 10 for LLMs and adversarial machine learning frameworks such as MITRE ATLAS.
  • Strong programming and scripting skills in Python, Go, C++, or Rust for custom tool development and exploit modification.
  • Deep understanding of attacker tradecraft, including advanced persistence, evasion techniques, memory injection, and lateral movement across on-premise and AWS/Azure cloud environments.
  • Familiarity with PyTorch, TensorFlow, Hugging Face, and enterprise deployment of AI frameworks and libraries.
  • Ability to translate technical exploit chains and zero-day research into strategic risk assessments for executive leadership.

Nice to have

  • Published security research, CVEs, bug bounty successes, or conference talks, particularly in AI security or novel exploitation techniques.
  • 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.
  • Contribute to the broader security community through research publications, zero-day disclosures, and conference presentations.
  • hirify.global promotes a diverse workplace and equal employment opportunities.

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 →