AI Red Team Engineer — Break LLMs, Build Safety (Equity)

Moonfire; San Francisco (CA); On-site; USD 170,000 - 230,000; Full time

Benefits offered by this job

Equity

Flexible Time Off

Language lessons (English/French)

Learning and development support

Hardware, tools, and subscriptions

Team off-sites

Job summary

White Circle in San Francisco hosts a role for an AI Red Team Engineer to break LLM-powered systems responsibly, automate attacks, and convert findings into actionable reports for demos, reviews, and sales.

You will own hands-on adversarial testing end to end, scripting attacks, and building an internal library of test cases and regression suites to improve safety and reliability of AI systems.

Qualifications

• Hands-on with QA automation, AppSec, API/security testing, or bug bounty.
• Proven experience breaking LLM-powered systems with adversarial testing.
• Strong Python scripting and automation skills.
• Experience testing APIs, web apps, backends, or SaaS products.

Responsibilities

• Red-team LLM-powered systems: chatbots, copilots, RAG pipelines, AI agents, tool-calling workflows.
• Test for jailbreaks, prompt injection, system-prompt and tool leakage, data leakage, unsafe outputs, policy bypass, tool misuse, token-cost 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.

Skills

Python scripting

QA automation

AppSec

API security testing

Penetration testing

LLM testing

Tools

Burp Suite

Postman

Playwright

pytest

LangChain

LangGraph

LlamaIndex

Job description

White Circle in San Francisco hosts a role for an AI Red Team Engineer to break LLM-powered systems responsibly, automate attacks, and convert findings into actionable reports for demos, reviews, and sales.

You will own hands-on adversarial testing end to end, scripting attacks, and building an internal library of test cases and regression suites to improve safety and reliability of AI systems.