π 4 days ago
Improve the judgment and reliability of production AI security agents by advancing their reasoning, evaluations, model selection, and defenses against attacks such as prompt injection.
Improve the judgment and reliability of production AI security agents by advancing their reasoning, evaluations, model selection, and defenses against attacks such as prompt injection.
Build polished, full-stack product experiences for AI security agents, owning live agent monitoring and vulnerability workflows from API and data model through interface, launch, and iteration.
Research and build offensive security techniques, tools, and evaluations that help AI agents discover, exploit, and validate vulnerabilities in real customer environments.
Build and own production systems for AI-driven security, including a live security graph, cloud integrations, and agents that test, triage, and remediate vulnerabilities.
Page 1 Β· 4 results