обновлено 4 дня назад
AI Red Team Engineer (Cybersecurity)
Мэтч & Сопровод
Для мэтча с этой вакансией нужен Plus
Описание вакансии
Текст:
TL;DR
AI Red Team Engineer (AI Safety/Cybersecurity): Breaking LLM-powered systems responsibly and automating adversarial attacks with an accent on jailbreaks, prompt injection, and tool misuse. Focus on developing an internal attack library, converting failures into regression tests, and producing evidence for security reviews.
Location: Global; fully remote
Company
is an AI safety company building a platform for testing, enforcing, and continuously improving natural-language policies for AI systems.
What you will do
- Red-team chatbots, copilots, RAG pipelines, AI agents, tool-calling workflows, and API-based AI products.
- Test for jailbreaks, prompt injection, system-prompt and tool leakage, unsafe outputs, policy bypass, excessive agency, and business-logic abuse.
- Write Python automation for attack prompts, model API calls, response scoring, and repeatable reports.
- Build and maintain an internal library of prompts, scenarios, test cases, regression tests, scoring rubrics, and demo cases.
- Document model failures, their impact, reproduction steps, severity, and potential fixes.
- Support customer demos, security reviews, and sales conversations with credible security evidence.
Requirements
- Background in QA automation, application security, API or penetration testing, or bug bounty work.
- Strong Python scripting skills and experience testing APIs, web applications, backends, or SaaS products.
- Hands-on experience with LLMs, prompts, system instructions, RAG, agents, and tool or function calling.
- Ability to identify bypasses, abuse edge cases, chained failures, and meaningful customer risk.
- Ability to write clear, reproducible bug reports in English.
- Commitment to ethical, in-scope security testing and compliance with applicable law.
Nice to have
- Experience with Burp Suite, Postman, Playwright, or pytest.
- Experience with automated LLM red-teaming agents, evaluation pipelines, regression suites, dashboards, or CI-friendly security tests.
- Familiarity with LangChain, LangGraph, LlamaIndex, RAG pipelines, AI agents, tool calling, or LLM-as-judge evaluation.
- Knowledge of OWASP LLM Top 10, OWASP Web Top 10, MITRE ATLAS, or similar AI security taxonomies.
- Experience with security reports, trust and safety, abuse prevention, fraud, moderation, platform security, CTFs, or responsible-disclosure programs.
Culture & Benefits
- Full-time remote work with a small, focused team.
- Flexible time off.
- Language lessons in English or French.
- Support for courses, conferences, and professional development.
- Hardware, subscriptions, tools, and services needed for the role.
- Team off-sites twice a year.
Hiring process
- Introductory call with the Talent Team.
- Test assignment and technical interview.
- Final call with the CEO.
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 →
Похожие вакансии
9 дней назад
AI Security Engineer (Agentic Systems)
9 дней назад
Staff Applied ML Engineer (Federal/National Security)
180 000 - 240 000$
5 дней назад
AI Red Team Engineer
182 000 - 238 000$
5 дней назад
AI Security Researcher/Research Engineer (AI Security)
7 дней назад
Software Engineer (Machine Learning) (Cybersecurity)
10 дней назад