Cyber Evaluations Engineer
Core
Design and run capability, uplift, and safety evaluations for cyber-relevant model risks; execute safeguard-robustness testing before major model releases.
Role type
Senior IC ML safety and cyber-evaluations engineer
Builds
Layered abuse-detection architecture and internal tooling for running and scoring evaluations
Domain
AI safety + cybersecurity
Deliverable
production ML models
Required skills
ML evaluation design, cybersecurity (CTF, vulnerability research, exploit development), Python, stakeholder communication, tooling development
Preferred skills
offensive-security research, AI security benchmark development, adversarial/abuse-data analysis, AI/ML evaluation frameworks, coordinated vulnerability disclosure, ML-based abuse detection, active secret clearance
Technologies
Python
Responsibilities
Design and run capability, uplift, and safety evaluations for cyber-relevant model risks; Execute safeguard-robustness testing before major model releases; Design, prototype, and tune detection probes for cyber misuse; Build and maintain internal tooling for running and scoring evaluations
Seniority
Senior, hands-on IC