AI Red Team Engineer: Adversarial Testing & Security Demos

White Circle; United States; Remote; USD 150,000 - 210,000; Full time

Benefits offered by this job

Flexible Time Off

Language lessons to help you improve

Learning and development support for课程

All the hardware, subscriptions, tools

Team off‑sites twice a year

Job summary

White Circle is hiring an AI Red Team Engineer to responsibly break LLM-powered systems, automate attacks, and convert findings into evidence for demos, security reviews, and sales conversations.

You will own hands‑on adversarial testing end to end: identify failures, prove them, script them, and document results for stakeholders. A strong background in QA automation and API security is essential.

Qualifications

• 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 injections, data leakage, tool misuse).

Responsibilities

• Red-team LLM-powered systems: chatbots, copilots, RAG pipelines, AI agents, tool-calling workflows.
• Test for jailbreaks, prompt injections, system prompts leakage, and unsafe outputs.
• Write lightweight Python to automate attacks, run prompt sets, and generate reports.
• Build and maintain an internal attack library: prompts, test cases, and demos.
• Turn model failures into clear reports with reproduction steps and impact analysis.
• Convert successful attacks into regression tests and product requirements.

Skills

Python scripting

QA automation

API/security testing

LLM safety/adversarial testing

Bug report writing

Tools

Burp Suite

Postman

Playwright

pytest

LangChain

LangGraph

LlamaIndex

RAG pipelines

AI agents

tool/function calling

Job description

White Circle is hiring an AI Red Team Engineer to responsibly break LLM-powered systems, automate attacks, and convert findings into evidence for demos, security reviews, and sales conversations.

You will own hands‑on adversarial testing end to end: identify failures, prove them, script them, and document results for stakeholders. A strong background in QA automation and API security is essential.