Senior AI Security Researcher
Core
Research emerging risks in AI agents and models, build guardrails and red teaming tests, and publish threat intelligence for enterprise AI security.
Role type
Senior AI Security Researcher (Agentic AI)
Builds
Guardrails, red teaming tests, sandboxes, detectors, graders, and regression tests for the Alice platform.
Domain
AI Security / Agentic AI / Enterprise Security
Deliverable
production ML models
Required skills
Security research, offensive security, penetration testing, vulnerability research, Python, agent frameworks, AI security frameworks (OWASP, MITRE ATLAS), experiment design, technical writing
Preferred skills
Published research, CVEs, conference talks, bug bounty/CTF records, adversarial machine learning, AI safety failure research, detection system evaluation, product collaboration
Technologies
Agent frameworks, MCP servers, workflow tools, AI gateways, Python
Responsibilities
Research agent risks (prompt injection, tool misuse, data exfiltration), build test environments and sandboxes, shape platform guardrails, inform go-to-market and threat intelligence, publish research and CVEs, collaborate with research organization
Seniority
Senior, hands-on IC
