← All roles

AI Red Team Engineer

White Circle· Research
Apply on company site
RemoteFull-timePosted 3mo ago

About the role

AI Red Team Engineer to adversarially test LLM-powered systems, automate attacks, and convert findings into evidence for customer demos, security reviews, and sales conversations. Owns end-to-end red-teaming: identify failures, prove them, script tests, and document results.

Responsibilities

  • Red-team LLM-powered systems: chatbots, copilots, RAG pipelines, AI agents, tool-calling workflows, and API-based AI products
  • Test for jailbreaks, prompt injection, system-prompt and tool leakage, sensitive-data and context leakage, unsafe outputs, policy bypass, tool misuse, excessive agency, resource and token-cost abuse, and business-logic abuse
  • Write lightweight Python to automate attacks, run prompt sets, call model APIs, collect and score responses, and generate repeatable reports
  • Build and maintain an internal attack library: prompts, scenarios, test cases, regression tests, scoring rubrics, and reusable demo cases
  • Turn model failures into clear reports: what happened, why it matters, how to reproduce it, how severe it is, and how to fix it
  • Convert successful attacks into regression tests and product requirements
  • Track new red-team and safety techniques and fold the useful ones into our tests
  • Support GTM by producing strong, credible evidence for customer demos, security reviews, and sales conversations

Qualifications

  • Genuinely love breaking things and reasoning adversarially
  • Background in QA automation, AppSec, API/security/pen testing, or bug bounty
  • Strong Python scripting skills
  • Experience testing APIs, web apps, backends, or SaaS products
  • Hands-on with LLMs, prompts, system instructions, RAG, agents, and tool/function calling
  • Understand LLM-specific abuse vectors (prompt injection, jailbreaks, data leakage, tool misuse, excessive agency, token-cost exhaustion)
  • Ability to find bypasses, abuse edge cases, chain failures, and reason about real-world impact
  • Ability to separate real customer risk from low-impact prompt tricks
  • Write clear, reproducible bug reports in clear English
  • Ability to move fast without perfect requirements
  • Firm ethical line: red-team to improve safety, operate within scope and law, avoid harmful material

Skills

Required:PythonAPI testingAdversarial testing / red-teamingBug reporting

Benefits

  • Competitive compensation package, including equity
  • Flexible Time Off
  • Language lessons (English or French)
  • Learning and development support for courses and conferences
  • All hardware, subscriptions, tools, and services needed
  • Team off-sites twice a year (e.g., Alps, Saint-Tropez, Marbella)
Last updated Sep 30, 2026. Interested? Apply on the company site.
White Circle logo

About White Circle

We keep your AI models safe, reliable, and secure.

We keep your AI models safe, reliable, and secure.

AI governanceAI safetycase studiescomplianceenterpriseheadline-ai-europe-100-2026model governancepolicy enforcement
Company profileWebsite

More open roles at White Circle