Staff AI Security Specialist

📋 Description

• Analyze security of AI agent systems to find vulnerabilities
• Design and build security controls for agentic systems
• Build working prototypes end to end, then harden with engineering
• Threat model new AI architectures before they ship
• Red-team AI agents and defenses: prompt injection, tool abuse, etc.
• Build repeatable evaluations and benchmarks for controls

🎯 Requirements

• 6+ years security/software engineering/applied research, 2+ with AI/ML
• Knowledge of agent harness, tool-calling loop, sandboxing
• Knowledge of agent memory, retrieval, orchestration (MCP)
• Depth in one security domain: appsec, offensive, identity, detection
• Understanding of AI threat landscape: OWASP, MITRE ATLAS
• Proficiency in Python to build and ship working systems