Senior AI Security Researcher
Core
Lead offensive security research against AI agents and infrastructure, developing automated attack tooling and turning findings into product detections and defences.
Role type
Senior IC offensive security researcher (AI agents)
Builds
Automated attack tooling, reusable evaluation suites, detection rules, classifiers, and policy controls
Domain
AI security, cybersecurity, autonomous agents
Deliverable
production ML models
Required skills
Offensive security, application security, red teaming, vulnerability research, LLM application attacks, tool calling, retrieval, memory, permissions, Python, systems languages
Preferred skills
MITRE ATLAS, OWASP Top 10 for LLM applications
Technologies
Python, systems languages
Responsibilities
Red-team AI agents across browser, code, enterprise and multi-agent environments; Research prompt injection, tool abuse, memory poisoning, identity and data-exfiltration attack chains; Build automated attack tooling and reusable evaluation suites; Turn findings into detection rules, classifiers and policy controls; Lead customer assessments and write findings
Seniority
Senior, hands-on IC