Назад
Company hidden
обновлено 2 месяца назад

AI Security Researcher (AI Security)

214 000 - 280 000$
Формат работы
onsite
Тип работы
fulltime
Грейд
senior
Английский
b2
Страна
UK/US
Вакансия из списка Hirify.GlobalВакансия из Hirify RU Global, списка компаний с восточно-европейскими корнями
Для мэтча и отклика нужен Plus

Мэтч & Сопровод

Для мэтча с этой вакансией нужен Plus

Описание вакансии

Текст:
/
TL;DR
AI Security Researcher (AI Security): Identifying, researching, and remediating conventional and AI-agent security threats across Apollo's internal software, infrastructure, and agent access controls with an accent on offensive security, threat modeling, and durable engineering controls. Focus on red-teaming agent sandboxes, modeling insider-risk attack trajectories, building high-signal detections, and hardening systems against novel AI security threats.

Location: In-person role based in the London or San Francisco office, with some work-from-home arrangements and flexible working hours.

Salary: San Francisco $214,000–$280,000; London £144,000–£189,000.

Company

hirify.global works with frontier AI companies on scheming research, model evaluations, control and monitoring, and AI agent security through its Watcher product.

What you will do

  • Protect Apollo’s internal software, infrastructure, and AI agent access controls.
  • Red-team internal systems and agent sandboxes, building realistic attack trajectories.
  • Design security solutions for novel and emerging AI-agent threats where existing playbooks do not apply.
  • Track adversary tactics and translate threat intelligence into high-signal detections.
  • Own security findings through remediation by building checks, tests, defaults, detections, and CI/CD integrations.
  • Collaborate with engineers, security staff, and technical teams working on scheming research and products.

Requirements

  • 5+ years of hands-on technical security experience, excluding purely GRC or compliance-focused work.
  • Direct experience with offensive security, threat modeling, red teaming, application security, or cloud security.
  • Ability to read code, understand infrastructure, evaluate technical controls, and reason about failure modes.
  • Engineering mindset with experience translating findings into automated controls, detection rules, adversarial test suites, paved roads, or CI/CD integrations.
  • Strong written communication for threat models, reports, and failure-mode documentation.
  • Comfort working at startup pace in an ambiguous, fast-changing environment.

Nice to have

  • Experience with AI/ML systems security or LLM security.
  • Detection engineering, SOC, or incident analysis experience.
  • Familiarity with insider threat programs or insider risk frameworks.

Culture & Benefits

  • Flexible working hours and schedule with some work-from-home arrangements.
  • Unlimited vacation and sick leave.
  • Up to six months of paid parental leave.
  • Health, dental, and vision insurance, plus retirement savings with employer matching, including 401(k) for US employees.
  • Paid work trips, staff retreats, relevant conferences, and a $1,000 annual professional development budget.
  • Visa sponsorship is available in the UK and US, with relocation support and visa fees where applicable.

Hiring process

  • Screening interview followed by a take-home test of approximately 2–3 hours.
  • Three technical interviews and a final interview with the CEO.
  • No LeetCode-style general coding interviews; AI tools may be used for the take-home test.

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 →