- Build and scale internal and external red-teaming tools and products to improve testing speed, coverage, and severity of findings.
- Develop agentic systems to explore attack spaces and identify and integrate new public jailbreaks and other releases.
- Advance attacker simulation and harmfulness evaluation; maintain vulnerability databases, statistical analysis tools, and reporting infrastructure.
- Build systems and workflows that support high-stakes red-teaming engagements with frontier AI companies and governments.
- Contribute to red-teaming frontier models and improve testing systems based on engagement insights.
- Plan sprints and lead engineering execution, translating technical goals into scalable plans, teams, and systems.
- Manage, mentor, and support engineering and red-teaming individual contributors; hire engineering managers and other roles as needed.
- Create processes for high-tempo engagements and design hiring pipelines in partnership with the red team and recruiting team.
- Identify engineering bottlenecks, prioritize solutions, and contribute to the red team’s technical and product strategy.
PythonArtificial IntelligenceCybersecurity+3 more