Senior Staff Security Engineer (AI Safeguards)

Quick Facts

• Role: Senior Staff Security Engineer (AI Safeguards)
• Focus: Security design and evaluation for ML/LLM safeguards

Description

You will keep a current map of ML usage and safeguards across products and lead the security design of new ML features. You’ll test and harden safeguards against jailbreaks, prompt injection, prompt leaks, and toxicity by turning findings into eval cases that run continuously across model, prompt, and safeguard changes. You will also design mitigations with ML engineers and define and report security metrics to prove safeguards are working.

Responsibilities

• Maintain the map of ML usage and safeguards across products
• Lead security design for new ML features
• Conduct boundary testing for jailbreaks, prompt injection, prompt leaks, and toxicity
• Convert discoveries into eval cases that run on every model/prompt/safeguard change
• Build mitigations with ML engineers that remain effective when detection misses
• Define security metrics and report on safeguard performance
• Review changes that could weaken safeguards
• Track AI attack research and translate new techniques into tests and mitigations

Requirements

• 8+ years in security engineering, including 2+ years in AI or LLM security
• Hands-on adversarial experience (red teaming, penetration testing, or vulnerability research) applied to LLM systems
• Deep knowledge of LLM attacks and defenses (e.g., OWASP Top 10 for LLM Applications, MITRE ATLAS)
• Ability to identify risks, develop mitigation plans, and implement fixes
• Strong coding skills in Python or Go and a record of shipping production code
• Enough ML fundamentals to build evals and judge classifier efficacy

Benefits

• Base pay guideline: $201,300–$352,300 plus equity (when applicable), variable/incentive compensation, and benefits
• Health plans, flexible spending accounts, 401(k) match, ESPP, matching donations, flexible time away, and family leave programs