Senior Security Researcher - Red Team
Core
Design and execute end-to-end attacks against agentic systems, AI-enabled security products, and orchestration frameworks to identify vulnerabilities like indirect prompt injection, sandbox escapes, and confused-deputy behavior.
Role type
Senior Security Researcher (Red Team)
Builds
Automated attack suites, high-fidelity test environments, regression evaluations, and adversarial scenarios.
Domain
AI Security / Agentic Systems / Offensive Security
Deliverable
production ML models
Required skills
Offensive security, agent security, cloud security, identity security, application security, exploitation, programming, engineering, large language model testing, multi-agent orchestration testing, secure agent architecture knowledge, threat modeling, technical communication.
Preferred skills
Experience with indirect prompt injection, cloud identity, authorization, sandboxing, container security, web exploitation, offensive-security operations, human-in-the-loop controls.
Responsibilities
Design and execute attacks against agentic systems; build realistic attack chains using attacker-controlled inputs; develop automated attack suites and test environments; create rigorous threat models and assess exploitability; partner with engineers to drive findings to remediation; convert weaknesses into automated tests and safer system designs; communicate attack paths and risk to leadership; track emerging attack techniques and evolve methods.
