Senior Staff Security Engineer
Core
Maintain the map of ML usage and safeguards across products and lead security design for new ML features.
Role type
Senior Staff Security Engineer (AI/LLM)
Builds
Mitigation mechanisms and defenses for LLM systems
Domain
Artificial Intelligence / Large Language Models
Deliverable
production ML models
Required skills
Adversarial testing, Red teaming, Python, Go, OWASP Top 10 for LLM Applications, MITRE ATLAS, Risk identification, Mitigation planning, Production code shipping, ML fundamentals
Preferred skills
Vulnerability research, Jailbreak testing, Prompt injection testing, Prompt leak testing, Toxicity analysis, AI attack research tracking
Responsibilities
Perform adversarial testing of jailbreaks, prompt injection, prompt leaks, toxicity, and other LLM attack techniques. Convert security findings into evaluation cases that run across model, prompt, and safeguard changes. Design and build mitigation mechanisms with ML engineers. Define and report security metrics measuring safeguard effectiveness. Review changes that could weaken safeguards.
Seniority
Senior Staff, hands-on IC
