AI Red Team Engineer

White Circle
Paris, United Kingdom
Workplace: RemoteFull timeUSD 60,000 - 90,000 annuallyFunction: Data Science & Machine LearningSkills: ["Adversarial reasoning","Ethical judgment","Attention to detail","Communication","Ability to move fast"]

Own end-to-end adversarial testing for LLM-powered systems, from finding failures to proving them with repeatable attacks and clear evidence. Test chatbots, copilots, RAG pipelines, and tool-calling workflows for jailbreaks, prompt injection, leakage, unsafe outputs, and business-logic abuse. Automate attacks with Python, maintain an internal attack library, and turn results into regression tests, product requirements, and customer-facing security demos.

Loading

Loading job details...

Preparing the role view and application actions.

FursaFursa
White Circle
White Circle
2 months ago

AI Red Team Engineer

✓ Verified Job

Canonical indexed version, validated from employer's careers page.

Source: Company careers pageValidated by: Fursa AI
Last checked: 11 hours agoStatus: Live

Job Summary

Own end-to-end adversarial testing for LLM-powered systems, from finding failures to proving them with repeatable attacks and clear evidence. Test chatbots, copilots, RAG pipelines, and tool-calling workflows for jailbreaks, prompt injection, leakage, unsafe outputs, and business-logic abuse. Automate attacks with Python, maintain an internal attack library, and turn results into regression tests, product requirements, and customer-facing security demos.
Location: Paris, United Kingdom
Workplace: Remote
Employment Type: Full time
Job Function: Data Science & Machine Learning

Key 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/tool leakage, sensitive-data/context leakage, unsafe outputs, policy bypass, tool misuse, excessive agency, and resource/token-cost abuse.
  • •Write Python to automate attacks, run prompt sets, call model APIs, collect/score responses, and generate repeatable reports.
  • •Build and maintain an internal attack library with prompts, scenarios, test cases, regression tests, scoring rubrics, and demo cases.
  • •Translate findings into clear reports, regression tests, and product requirements to support customer demos and security/sales conversations.

Pay and Benefits

Salary: USD 60,000 - 90,000 annually
Equity and Bonus:Equity
Perks:Paid LeaveHealth InsuranceRelocation

Key Requirements

  • •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.
  • •Ability to write clear, reproducible bug reports in English.
Experience:AI safetyLLM testingSecurity testingRAGAPI security
Skills:Adversarial reasoningEthical judgmentAttention to detailCommunicationAbility to move fast
Languages:English
Tech Stack:PythonLLMsPrompt injectionJailbreaksRAG pipelinesAI agentsTool/function callingBurp SuitePostmanPlaywrightPytestLangChainLangGraphLlamaIndexLLM-as-judgeOWASP LLM Top 10OWASP Web Top 10MITRE ATLAS

Company Brief

White Circle
Builds AI-driven products and services to help businesses automate workflows, extract insights from data, and improve decision-making using machine learning and natural language processing technologies.
Industry: AI & Machine Learning
Website