AI Red Team Engineer
Core
Responsible adversarial testing of LLM-powered systems to find failures, automate attacks, and generate evidence for security reviews and customer demos.
Role type
Senior IC AI Red Team Engineer
Builds
Automated attack scripts, internal attack libraries, regression tests, and security reports for LLM products.
Domain
AI Safety / LLM Security / Adversarial Testing
Deliverable
production ML models | product features | dashboards & analysis
Required skills
Python scripting, API security testing, LLM adversarial testing, prompt injection analysis, bug report writing, ethical red-teaming
Preferred skills
Burp Suite, Postman, Playwright, pytest, LangChain, LangGraph, LlamaIndex, OWASP LLM Top 10, MITRE ATLAS, CTF/red-team competition experience
Technologies
Python, LangChain, LangGraph, LlamaIndex, RAG pipelines, AI agents, OWASP LLM Top 10, MITRE ATLAS
Responsibilities
Red-team LLM-powered systems (chatbots, copilots, RAG, agents), automate repetitive attacks via Python scripts, build and maintain internal attack libraries, convert model failures into reproducible reports and regression tests, support GTM with credible security evidence
Seniority
Senior, hands-on IC