Назад
Company hidden
3 дня назад

AI Security & Control Engineer (AI)

180 000 - 270 000$
Формат работы
onsite
Тип работы
fulltime
Грейд
senior
Английский
c1
Страна
UK/US
Релокация
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 & Control Engineer (AI): Designing threat models and control protocols for coding agents with an accent on adversarial AI, product security infrastructure, and insider risk. Focus on building adversarial test suites, reducing the attack surface of AI products, and aligning technical controls with enterprise security needs.

Location: On-site in London or San Francisco. Visa sponsorship and relocation support are available for the UK and US.

Salary: $180k – $270k (135k – 200k GBP)

Company

hirify.global develops tools to prevent harms from widely deployed AI systems, focusing on detecting and mitigating deceptive alignment.

What you will do

  • Develop threat models and kill chains for coding agents using an insider risk lens.
  • Design attack trajectories and exploits to improve the effectiveness of AI monitors.
  • Own AppSec standards, container hardening, and secrets management for product infrastructure.
  • Manage security questionnaires, whitepapers, and customer pen-test support.
  • Red-team 'Watcher' to identify and fix failure modes.
  • Collaborate with research and engineering teams to define tenant isolation and data retention policies.

Requirements

  • 5+ years of hands-on technical experience in security roles.
  • Proven expertise in application security, cloud security, or product security.
  • Ability to read code and evaluate technical controls (engineering mindset).
  • Strong understanding of enterprise security buyer priorities and CISO concerns.
  • Excellent written communication for producing precise technical artifacts.
  • Must be based in or able to relocate to London or San Francisco.

Nice to have

  • Experience with LLM security, AI control research, or AI/ML systems.
  • Background in detection engineering, SOC, or incident analysis.
  • Experience with insider threat frameworks or offensive security/red teaming.
  • Experience working at a security vendor or product company.
  • Formal AI safety research background.

Culture & Benefits

  • Market competitive salary and equity.
  • Unlimited vacation and sick leave.
  • Comprehensive health, dental, and vision insurance.
  • Retirement savings with employer matching (e.g., 401k in US).
  • Daily lunch, dinner, and snacks provided.
  • $1,000 yearly professional development budget.

Hiring process

  • Screening interview.
  • Take-home test (approx. 2 hours).
  • Three technical interviews focused on job-related tasks.
  • Final interview with the CEO.

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 →