Security Researcher — Adversarial AI & Detection

raydar; San Francisco (CA); On-site; USD 175,000 - 225,000; Full time

Job summary

Raydar is hiring a Security Researcher in San Francisco to advance offensive techniques against developer tools and automated assistants. You will conduct adversarial testing, publish analyses for security leadership, and translate findings into practical detections and enforcement policies.

The role emphasizes independent, frontier problem solving and hands-on work with models and tools on-site in San Francisco.

Qualifications

• Two to ten years of experience in adversarial testing, threat analysis, or building detections within a security practice.
• Background in security work at a security software vendor, inside a corporate security group, or on a research team at an AI developer.
• Hands-on experience attacking models or agent tooling through prompt injection, jailbreaks or tool misuse.
• Able to work on-site five days a week.

Responsibilities

• Probe developer tools and AI assistants for weaknesses using adversarial methods.
• Run comparative studies of attack success across open-source and proprietary models.
• Publish research and findings written for security leadership audiences.
• Convert findings into detections and enforcement policies, and investigate real incidents in customer environments.
• Brief senior security stakeholders on emerging risks.

Skills

Adversarial testing

Threat analysis

Detections development

Job description

Raydar is hiring a Security Researcher in San Francisco to advance offensive techniques against developer tools and automated assistants. You will conduct adversarial testing, publish analyses for security leadership, and translate findings into practical detections and enforcement policies.

The role emphasizes independent, frontier problem solving and hands-on work with models and tools on-site in San Francisco.