AI Safety & Red Teaming Lead (AI)

Location: San Francisco, California, United States; onsite work required

Salary: $130K–$150K base annually; $350K OTE

Company

Fast-growing applied AI company building reinforcement-learning environments, agents, and datasets for leading frontier AI labs.

What you will do

• Design adversarial datasets and safety benchmarks for improving foundation models.
• Jailbreak and stress-test frontier models to identify failure modes and unsafe behavior.
• Partner with lab researchers on model behavior, safety evaluation, and risk priorities.
• Write precise risk specifications based on harm taxonomies, safety frameworks, and model policy.
• Build automated red-teaming and evaluation pipelines in Python.
• Help establish standards and processes for scaling safety work.

Requirements

• 2+ years of experience in AI safety, red teaming, trust and safety, adversarial machine learning, or security research.
• Hands-on experience with model jailbreaking, prompt-injection research, offensive security, penetration testing, bug bounty work, CTFs, or trust and safety investigations.
• Fluency with harm taxonomies, evaluation design, safety frameworks, and model policy.
• Python proficiency and the ability to write production-quality code.
• Strong writing skills and the ability to specify risk precisely.
• Ability to work onsite in San Francisco.

Nice to have

• Published safety, alignment, or security research.
• Bug bounty, CTF, or red-teaming competition experience.
• Expertise in high-consequence risk domains such as cyber, bio, fraud, child safety, or influence operations.

Culture & Benefits

• High-agency role within a small, rapidly scaling team.
• Direct collaboration with frontier AI labs.
• Hands-on individual-contributor and leadership responsibilities.
• Opportunity to shape safety standards as the function grows.