Applied Scientist, AGI/AI Security
Core
Research and develop novel security validation and monitoring techniques for AI systems at scale, focusing on real-time agent monitoring, automated remediation, application validation, and AI asset discovery.
Role type
Senior Applied Scientist (AI Security)
Builds
Production security solutions for AI agents, including detection models, validation engines, protection technologies, and asset discovery systems.
Domain
AI Security, Machine Learning, Cryptography, Automated Reasoning
Deliverable
production ML models | product features
Required skills
AI security research, real-time behavioral analysis, adversarial robustness evaluation, automated reasoning, cryptography, scalable system design, Java/C++/Python programming, algorithms and data structures, parallel and distributed computing
Preferred skills
Unix/Linux usage, professional software development experience
Technologies
graph-based anomaly detection, NLP-based service classification, code/traffic analysis, private inference
Responsibilities
Design and implement scientific approaches for continuous behavioral analysis of AI agents; invent and deliver novel protection technologies and automated remediation techniques; develop scalable methodologies for security testing of AI applications; research and build techniques to automatically discover and catalog AI-enabled applications; write critical-path code for detection models and validation engines; publish research results at peer-reviewed venues.
Seniority
Senior, hands-on IC with research leadership