Назад
Company hidden
3 дня назад

Principal AI Security Researcher (AI)

Формат работы
remote
Тип работы
fulltime
Грейд
senior
Английский
b2
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

Principal AI Security Researcher (AI): Leading original security research on agentic AI systems and AI-powered browsers with an accent on identifying novel attack vectors and adversarial techniques. Focus on defining the long-term AI security roadmap, conducting red team exercises, and establishing the company as a thought leader in the AI security community.

Company

hirify.global is a global software company focused on building innovative browsers and AI-powered products.

What you will do

  • Lead original security research on agentic AI, multi-agent workflows, and MCP-based architectures.
  • Identify, validate, and demonstrate novel attack vectors against AI systems.
  • Define the long-term AI security research roadmap and threat landscape.
  • Publish high-quality technical research, whitepapers, and vulnerability disclosures.
  • Conduct security assessments, architecture reviews, and red team exercises.
  • Collaborate with engineering teams to translate research into secure product designs.

Requirements

  • Extensive experience in offensive security research, vulnerability discovery, or AI security.
  • Demonstrated record of impactful security findings, CVEs, or offensive research.
  • Deep understanding of LLM applications, agentic frameworks, and adversarial AI techniques.
  • Strong software engineering capabilities for developing research tooling and proof-of-concepts.
  • Recognized presence in the security research community through talks or publications.
  • Ability to lead research initiatives independently in ambiguous environments.

Nice to have

  • Speaking experience at major security conferences like Black Hat or DEF CON.
  • Published peer-reviewed academic work in AI security.
  • Experience leading AI red teaming programs.
  • Contributions to AI security standards or open-source tooling.

Culture & Benefits

  • Work in a diverse, inclusive, and supportive professional environment.
  • Flat organizational structure with short decision-making paths.
  • Focus on creativity, collaboration, and smart technology usage.
  • Support for ongoing skill development and professional growth.

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 →