AI Red Team Engineer (Cybersecurity)

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: Remote (Global) or Hybrid in Paris, France

Salary: $60,000 – $90,000 + Equity

Company

AI Safety company building a reliability and optimization layer for AI systems using natural-language policies.

What you will do

• Red-team LLM-powered systems including chatbots, copilots, RAG pipelines, and AI agents.
• Automate attacks, prompt sets, and report generation using lightweight Python scripting.
• Build and maintain an internal attack library consisting of scenarios, test cases, and scoring rubrics.
• Convert model failures into detailed reports and subsequent regression tests or product requirements.
• Track and integrate new red-team and safety techniques into existing tests.
• Support GTM by producing credible evidence for customer demos and security reviews.

Requirements

• Background in QA automation, AppSec, API/security/pen testing, or bug bounty.
• Strong Python scripting skills and experience testing APIs or SaaS products.
• Hands-on experience with LLMs, prompts, RAG, agents, and tool-calling.
• Deep understanding of LLM abuse vectors such as prompt injection and jailbreaks.
• English: Proficiency required to write clear, reproducible bug reports.
• Ethics: Must operate within scope and the law.

Nice to have

• Experience with Burp Suite, Postman, Playwright, and pytest.
• Familiarity with LangChain, LangGraph, LlamaIndex, and LLM-as-judge evaluation.
• Knowledge of OWASP LLM Top 10, OWASP Web Top 10, or MITRE ATLAS.
• Track record in CTFs, red-team competitions, or responsible-disclosure programs.
• Experience building eval pipelines, regression suites, or CI-friendly security tests.

Culture & Benefits

• Remote-first approach with paid time off based on local regulations.
• Option to work from the Paris office with a relocation package.
• Premium medical insurance provided in France.
• Provision of all necessary hardware, tools, and paid subscriptions for AI agents.
• Bi-annual team off-sites (e.g., Alps, Saint-Tropez).

Hiring process

• Introductory call with HR (25 min).
• Take-home technical test task.
• Technical interview (60 min).
• Final conversation with the CEO (45 min).