about 2 hours ago
Base Salary
$347k - $490k/yr
Responsibilities
- Serve as the technical owner of OpenAI’s offensive security agents.
- Design and build specialized agents for continuous testing of infrastructure and applications.
- Translate offensive security workflows into tools and internal knowledge bases.
- Develop capabilities for testing cloud, Kubernetes, and web applications.
- Build complete vulnerability-management loops from discovery to fix verification.
- Design human-in-the-loop systems for agent oversight and context provision.
- Create feedback mechanisms for agents to learn from domain experts.
- Develop evaluations to measure security outcomes and agent capabilities.
- Build production-quality infrastructure for continuous operation and recovery.
- Investigate agent failures and improve surrounding tools and workflows.
- Collaborate with various security and engineering teams to ensure actionable findings.
Requirements
- Substantial hands-on offensive security experience.
- Extensive domain expertise in cloud security, Kubernetes, and web application security.
- Experience assessing complex, customized environments.
- Ability to decompose ambiguous security problems into reliable systems.
- Experience building production-quality software.
- Experience with agent systems that utilize models and feedback loops.
- Strong understanding of model capabilities and limitations.
- Excitement for working with frontier models and improving workflows.
- Desire to serve as a technical owner and make foundational architectural decisions.