Staff AI Secuirty Researcher
Core
Leading efforts to identify and understand security risks unique to AI systems, including LLMs, agentic workflows, and infrastructure flaws.
Role type
Staff AI Security Researcher (IC)
Builds
Agentic detection and response capabilities, automated probing tools, and threat models for emerging AI systems.
Domain
Cybersecurity, AI/ML Security, Adversarial ML
Deliverable
production ML models
Required skills
Adversarial ML techniques (prompt injection, jailbreaking, data poisoning), Offensive security research, Python/JavaScript/Java, Cloud environments (AWS/GCP/Azure/Kubernetes), Technical writing, Cross-functional leadership
Preferred skills
Publication record in security research or AI safety, Experience leading cross-functional technical initiatives
Technologies
LLMs, SLMs, Agentic systems, OWASP Top 10 for LLMs, MITRE ATLAS, Kubernetes, AWS, GCP, Azure
Responsibilities
Conduct advanced research on AI vulnerabilities (prompt injection, data exfiltration, misuse vectors); Build threat models for agentic systems and tool use; Design automated tools to probe AI security at scale; Partner with engineering to translate findings into detection capabilities; Stay informed on adversarial ML trends; Mentor researchers and engineers; Publish research findings.
Seniority
Staff, hands-on IC with mentorship
