Sr. Staff AI Engineer
Core
Building AI-based evaluations and security testing workflows for AI Assets (LLMs, MCP servers, AI Apps) to detect security risks and adversarial intent.
Role type
Sr. Staff AI Engineer (Red Teaming)
Builds
AI security evaluation pipelines, red teaming tools, and products for AI asset security
Domain
Cybersecurity / AI Security / LLM Security
Deliverable
production ML models
Required skills
Python, LLMs, AI/ML technologies, MCP (Model Context Protocol), end-to-end project leadership, AI security methodologies
Preferred skills
Automated framework vulnerabilities, adversarial ML exploits, LLM evaluation, AI red teaming workflows, product direction ownership
Technologies
Python, LLMs, MCP, AI/ML frameworks
Responsibilities
Create and extend LLM/MCP/AI App benchmarking and security evaluation pipelines; Own technical vision and architecture for red teaming tools; Lead design and execution of red team exercises against AI Assets; Improve internal tooling and operational processes for AI evaluations; Track advances in AI security and adversarial ML
Seniority
Sr. Staff, hands-on IC with strategic ownership