Senior Security Researcher (AI)
Мэтч & Сопровод
Для мэтча с этой вакансией нужен Plus
Описание вакансии
TL;DR
Senior Security Researcher (AI): Investigating evolving adversarial tradecraft exploiting generative AI systems including LLMs, autonomous agents, and on-device assistants with an accent on jailbreak methods, prompt engineering, and AI-enabled attack vectors. Focus on conducting hands-on research, translating findings into defensive product improvements, and producing public-facing security content.
Location: Distributed team across US, Canada, Australia, and Israel
Company
Building the endpoint AI observability platform to maximize productivity and safety of AI adoption in organizations, backed by top VC firms like Sequoia Capital.
What you will do
- Conduct in-depth research on how adversaries exploit generative AI tools like LLMs, autonomous agents, and on-device assistants
- Perform hands-on experiments with adversarial prompting, jailbreaks, computer use agents, and other AI attack vectors
- Translate research into actionable product improvements for Origin’s platform
- Produce public-facing security research including blog posts and conference talks
- Stay current on offensive and defensive security techniques and support team initiatives
Requirements
- 5+ years in offensive security research (red team, purple teaming) or defensive security research for publications and features
- Ability to write code for research tooling development
- Strong ability to explain complex technical concepts to executives and technical audiences
- Aptitude for fast-paced startup environment
Nice to have
- Experience with generative AI exploitation, prompt engineering, jailbreaks, or agentic misuse
- Familiarity with reinforcement learning, model interpretability, or AI safety
- Contributions to open-source AI or security tools
- Prior publications or conference talks
- Proficiency in systems languages like Rust or C/C++
- Knowledge of OS internals and reverse engineering
Culture & Benefits
- Distributed team with culture of trust, autonomy, and excellence
- Empowerment to take ownership and continuously improve
- Generous healthcare, flexible PTO, and home-office support
- High standards for top performers aligned with mission
- Focus on quality, collaboration, and impactful security solutions
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 →