Назад
Company hidden
10 дней назад

Senior GenAI Safety Researcher (Frontier Risk)

Формат работы
remote (только USA)
Тип работы
fulltime
Грейд
senior
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
Senior GenAI Safety Researcher (Frontier Risk) (AI Safety/Cybersecurity): Leading frontier AI risk research, red-teaming datasets, evaluation protocols, and technical risk reports focused on CBRNE and cybersecurity threat vectors with an accent on multimodal analysis, dual-use risk assessment, and client-facing technical delivery. Focus on designing defensible evaluations, modeling residual risks, coordinating specialized experts, and developing architecture-level mitigations for emerging AI capabilities.

Location: Remote in the USA

Company

hirify.global, operating through Alice, provides trust, safety, and security solutions across the AI lifecycle, including model hardening evaluations, pre-deployment red-teaming, runtime guardrails, and drift detection.

What you will do

  • Lead red-teaming datasets, evaluation protocols, and technical risk reports across base models, guardrails, and agentic workflows in text, vision, and audio.
  • Coordinate subject-matter expert pools, allocate work, and maintain delivery speed under compressed client deadlines.
  • Review analytical outputs for technical rigor, methodological quality, defensibility, reproducibility, and dual-use containment alignment.
  • Lead client meetings, presenting threat models, residual risk levels, and architecture-level mitigations to engineering leaders.
  • Monitor emerging frontier capabilities and refine CBRNE and cyber evaluation frameworks for state-of-the-art dual-use risks.

Requirements

  • 2–4 years of experience spanning AI safety, red-teaming, CBRNE risk, or cyber threat intelligence.
  • Ability to drive complex technical projects and align specialized experts against demanding deadlines.
  • Sound technical judgment when navigating dual-use risks, hazardous materials, and sensitive cyber vulnerabilities.
  • Clear and persuasive communication skills, including translating high-stakes risk architectures for engineering and executive leadership.

Nice to have

  • Advanced degree in chemistry, biology, nuclear science, computer security, or AI.
  • Offensive security experience, including penetration testing, vulnerability research, or CTFs.
  • In-depth understanding of frontier AI evaluation benchmarks, capability threshold triggers, and lab preparedness frameworks.

Culture & Benefits

  • Remote work arrangement in the USA.
  • Work alongside trust, safety, and security specialists supporting frontier model labs, enterprises, and UGC platforms.
  • Contribute to safeguarding communicative technologies and AI platforms used by billions of people.

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 →