Senior Red Team Operator, AI/LLM

What you'll do

• Attack LLMs, agents, RAG pipelines, and related applications; prove exploitability and trace impacts across tools, identities, cloud, and data.
• Pressure-test autonomous agents and swarm operations, identify weaknesses, and encode expert tradecraft into techniques, decision logic, and evaluation data.
• Build automation and tooling, research emerging AI attack classes, and communicate attack findings and remediation to clients and internal teams.

What they ask for

• Hands-on LLM and agent exploitation, including prompt injection, jailbreak chains, system prompt extraction, and data exfiltration through model outputs.
• Depth in at least one additional AI attack surface: agentic systems, RAG and data pipelines, adversarial ML, or AI supply chain and infrastructure.
• Strong web and API exploitation skills, including authentication and authorization bypass and injection chains.
• Proficiency across Linux, Windows, and macOS; scripting in Python, Bash, or similar; must be eligible to work in the United States without sponsorship.

Nice to have

• Hands-on work building AI systems or ML pipelines; experience shipping offensive AI tooling or public AI security research.
• Working familiarity with MITRE ATLAS, the OWASP Top 10 for LLM Applications, or the NIST AI Risk Management Framework; relevant certifications.

Tools

Burp Suite, Caido, Garak, PyRIT, promptfoo, Adversarial Robustness Toolbox, Python, Bash

AI focus

Red-team LLMs, agents, RAG pipelines, and AI supply chains; test autonomous attacker agents and convert AI attack tradecraft into agent techniques, decision logic, and evaluation data.