Роль связана с безопасностью передовых ИИ-моделей, имеет понятную зону ответственности и сильные сигналы роста компании, но требует работы в офисе.
Базовая зарплата ниже рынка
Передовые технологии
Востребованное направление
Быстрый рост компании
?Только работа в офисе
Описание вакансии
Текст:
Hirify AI/Оригинал
TL;DR
AI Safety & Red Teaming Lead (Applied AI): Designing adversarial datasets, safety benchmarks, and automated red-teaming pipelines for frontier AI labs with an accent on model behavior, risk taxonomies, and safety evaluation. Focus on jailbreaking and stress-testing foundation models, specifying precise risks, and partnering with lab researchers on high-consequence safety challenges.
Location: Onsite in San Francisco, California, United States
Base compensation: $130K–$150K annually; OTE: $350K.
Company
Applied AI company building reinforcement-learning environments, agents, and datasets for frontier AI labs, with quality as a core differentiator and rapid expansion into new domains.
What you will do
Design adversarial datasets and safety benchmarks used to improve foundation models.
Jailbreak and stress-test frontier models to identify failure modes and unsafe behavior.
Partner with lab researchers on model behavior, safety evaluation, and risk priorities.
Write precise risk specifications grounded in harm taxonomies, safety frameworks, and model policy.
Build automated red-teaming and evaluation pipelines in Python.
Help establish standards and processes for the growing safety function.
Requirements
2+ years of experience in AI safety, red teaming, trust and safety, adversarial ML, or security research at a frontier AI lab, large technology company, top security firm, or equivalent.
Hands-on adversarial experience, such as jailbreaking frontier models, prompt-injection research, offensive security, penetration testing, bug bounty work, CTFs, or trust and safety investigations.
Fluency with harm taxonomies, evaluation design, safety frameworks, and model policy.
Python proficiency and ability to write production-quality code.
Strong writing skills and ability to specify risk precisely.
High agency and a competitive track record.
Able to work onsite in San Francisco.
Nice to have
Published safety, alignment, or security research.
Bug bounty, CTF, or red-teaming competition record.
Depth in a high-consequence risk domain such as cyber, bio, fraud, child safety, or influence operations.
Culture & Benefits
Hands-on individual-contributor-plus-lead role within a small, high-agency team.
Direct collaboration with frontier AI labs on AI safety and model behavior.
Opportunity to help define safety standards as the function scales.