Назад
Company hidden
1 день назад

Cybersecurity for AI Safety (Contract)

Формат работы
remote (только USA)
Тип работы
project
Английский
b2
Страна
US
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
Cybersecurity for AI Safety (Contract) (Cybersecurity/AI): Designing realistic cybersecurity prompts and evaluating AI-generated responses to improve the accuracy, usefulness, and safety of frontier AI systems with an accent on application security, network security, cloud infrastructure, vulnerability management, and secure software development. Focus on assessing sensitive dual-use scenarios, applying structured evaluation rubrics, and providing actionable feedback on model performance and reliability.

Location: United States (Remote)

Company

hirify.global is a Series A startup developing automated tools and expert datasets to improve human safety in the AI era, using psychology and clinical expertise.

What you will do

  • Design realistic, expert-level cybersecurity prompts covering application security, network security, cloud infrastructure, vulnerability management, and secure software development.
  • Evaluate AI-generated responses for technical accuracy, completeness, practical usefulness, and responsible handling of sensitive security topics.
  • Assess dual-use cybersecurity scenarios against project guidelines.
  • Apply structured evaluation rubrics to annotate prompts and model outputs consistently.
  • Provide clear, actionable feedback to improve the performance, safety, and reliability of frontier AI systems.

Requirements

  • Bachelor’s or Master’s degree in Computer Science, Cybersecurity, or a closely related technical field, or 5+ years of professional software engineering experience at a startup or technology company.
  • Deep knowledge of cybersecurity principles, modern software systems, and secure development practices.
  • Excellent written communication skills in English.
  • Strong technical reasoning and sound judgment when working with sensitive or dual-use security topics.
  • Ability to apply detailed guidelines while maintaining consistent, high-quality evaluations.

Nice to have

  • Experience in offensive security, penetration testing, vulnerability research, or security engineering.
  • Experience evaluating, reviewing, benchmarking, or red-teaming technical or AI-generated content.
  • Familiarity with AI evaluation, model assessment, or human-in-the-loop data annotation workflows.

Culture & Benefits

  • Contract, project-based engagement.
  • Hourly rate determined by experience and project parameters.
  • Rate disclosed before the project begins.
  • Work with a multidisciplinary team improving AI understanding of software security and cyber defense.

Hiring process

  • Applications are accepted and reviewed only through the official recruiting portal.

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 →