AI Security Researcher
Core
Build offensive AI agents and red team capabilities to defeat defensive security systems.
Role type
Senior IC AI Security Researcher (Offensive/Red Team)
Builds
Autonomous red team agents, agent harnesses, cyber ranges, and security benchmarks
Domain
Cybersecurity + Applied AI
Deliverable
production ML models
Required skills
Offensive security/red team operations, full-chain attack execution, C2 frameworks, payload development, detection evasion, Python coding, cyber range management, benchmark creation
Preferred skills
Cloud security, network attack experience, open-source contributions, AI agent/LLM tooling experience
Technologies
Python, Mythic, EDR, SIEM, Windows, Active Directory, MCP servers
Responsibilities
Design and build red team agents; extend agents to full-chain operations; build detection-evasion capabilities; design and operate cyber ranges; create security benchmarks; verify attack paths in customer environments; represent the company in the offensive security community
Seniority
Senior, hands-on IC
