Senior AI Security Researcher
Core
Define how frontier AI systems, agentic applications, and AI-enabled security automation are tested, attacked, defended, and safely deployed.
Role type
Senior IC AI security researcher
Builds
New methods, tools, evaluations, and proofs of concept for AI security
Domain
AI security, adversarial ML, cyber-defense research
Deliverable
production ML models | product features | research
Required skills
AI security research, adversarial ML, LLM security, threat modeling, exploit research, malware analysis, secure code review, incident-response automation, Python, PyTorch, JAX, TensorFlow, scikit-learn, Pandas, NumPy, Spark, BigQuery
Preferred skills
Published work in AI security, benchmark development, red-team tooling, low-level systems security, mentoring researchers
Technologies
Python, PyTorch, JAX, TensorFlow, scikit-learn, Pandas, NumPy, Spark, BigQuery
Responsibilities
Develop open-ended AI security research questions; build practical methods and prototypes to reveal AI system failures under adversarial conditions; explore AI security problems like prompt injection and data poisoning; translate research into usable outcomes for engineering teams; collaborate across security and AI teams; shape AI-security research strategy
Seniority
Senior, hands-on IC with strategy & mentorship
