AI Security Engineer: Guardrails & Safe AI Deployment

FinTech Collective, LLC; San Francisco (CA); On-site; USD 150,000 - 230,000; Full time

Benefits offered by this job

Equity

Commission

Medical, dental, vision, and 401(k)

Job summary

Plaid's Platform Security team is hiring a security-focused professional to be the first line of defense for AI security. You will review new AI technologies for risks, design guardrails and identity controls, and implement detection systems that allow AI to be used safely at scale.

Responsibilities include reviewing AI systems pre- and post-deployment, deploying guardrails and sandboxes, tracking AI identities, and mitigating prompt injection.

Qualifications

• Hands-on experience securing AI technologies with practical deployments.
• Experience designing guardrails, sandboxes, or controls for AI.
• Ability to manage AI identities and access.
• Experience running AI security reviews.
• Experience with AI security tooling (built or purchased).

Responsibilities

• Review AI systems and integrations for security risk before and after deployment.
• Design and deploy guardrails, sandboxes, and other controls.
• Build or implement systems to track and manage AI identities.
• Detect and mitigate prompt injection across Plaid's AI surface area.
• Run AI-focused security reviews and set security standards.
• Impact: fewer AI incidents, faster AI shipping, scalable controls.

Skills

Guardrails & Sandboxes

AI Identity Management

Prompt Injection Mitigation

AI Security Reviews

AI Security Tooling

Experience: 3-6 years

Job description

Plaid's Platform Security team is hiring a security-focused professional to be the first line of defense for AI security. You will review new AI technologies for risks, design guardrails and identity controls, and implement detection systems that allow AI to be used safely at scale.

Responsibilities include reviewing AI systems pre- and post-deployment, deploying guardrails and sandboxes, tracking AI identities, and mitigating prompt injection.