Назад
Company hidden
2 дня назад

AI Security Researcher/Research Engineer (AI Security)

Формат работы
remote (только Europe)/hybrid
Тип работы
fulltime
Английский
b2
Страна
UK/US/Europe
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
AI Security Researcher/Research Engineer (AI Security): Designing secure-by-design architectures and auditing LLM-powered web agents and chatbots with an accent on adversarial evaluations, prompt injection, tool abuse, and data exfiltration. Focus on analyzing frontier-model behavior, developing security-focused training and fine-tuning techniques, and translating research into measurable product security improvements.

Location: London, England preferred; exceptional candidates in the rest of Europe may be considered. Remote or hybrid.

Company

A privacy-focused technology startup building a web browser, private search engine, private AI assistant, and privacy-preserving advertising network.

What you will do

  • Design and execute adversarial evaluations for LLM-powered web agents and chatbots, including prompt injection, tool abuse, and data exfiltration scenarios.
  • Analyze model behavior and internal reasoning to understand and forecast security risks in frontier models.
  • Develop and prototype security-focused training and fine-tuning techniques.
  • Integrate information flow control, privilege control, and contextual security principles into web agents.
  • Collaborate with engineering, privacy, machine learning, and cryptography researchers to convert findings into product changes, tests, and measurable improvements.
  • Help define security strategy and responsible-release policies for web agents.

Requirements

  • Demonstrated experience with secure AI, including prompt injection attacks and security guardrails.
  • Strong publication record in AI security, ML security, or a closely related field.
  • Strong Python coding skills and familiarity with PyTorch or JAX.
  • Experience training, fine-tuning, and evaluating large language models.
  • Deep familiarity with large language models, web agents, and their training processes.
  • Experience applying information flow control, access control, or least-privilege principles.

Nice to have

  • Ph.D. in computer science, with exceptions considered for relevant industry experience.
  • Experience shipping products and features in a fast-moving environment.
  • Open-source security or privacy projects.
  • Experience with confidential computing and ZKP/SMPC protocols.
  • Publication record in premier systems, performance, or machine learning venues.

Culture & Benefits

  • Work with cutting-edge AI, privacy, and security technologies.
  • International startup environment with exposure to a global team.
  • Competitive compensation and opportunities for personal growth.
  • Remote or hybrid work options, with London as the preferred hiring location.

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 →