Cyber Security Engineer
Core
Designing benchmark tasks and evaluation environments to measure blue-team AI reasoning capabilities.
Role type
Contract cybersecurity engineer (AI evaluation)
Builds
Benchmark tasks, realistic evaluation environments (multi-host networks, Active Directory, cloud control planes), and infrastructure for reproducible AI measurement.
Domain
Cybersecurity + AI Research
Deliverable
production ML models
Required skills
Blue-team detection engineering, threat hunting, incident response, malware analysis, scripting, cloud/enterprise environment management
Preferred skills
None stated
Technologies
Active Directory, cloud control planes
Responsibilities
Design benchmark tasks grounded in real SOC work; Construct realistic evaluation environments; Define correct answers for blue-team AI reasoning; Build infrastructure to measure AI performance reproducibly at scale.
Seniority
Contract, hands-on IC