Prompt Injection Jobs in San Francisco, CA

…authority should come from, how prompt injection and exfiltration show up in practice

…detecting AI-specific abuse, such as prompt injection, model extraction, or anomalous API usage.

…risks, such as model abuse, prompt injection, data leakage, or misuse of

Detect and mitigate prompt injection across Plaid's AI surface area.

…Experience securing AI/ML applications, including prompt

injection, data exfiltration, and other adversarial risks.

…You… Interest in AI/LLM security, prompt injection, data poisoning, model extraction, etc.

Threat-model autonomous agent behavior: prompt injection, tool misuse, the "lethal trifecta" of untrusted input + sensitive data + external action

injection, model extraction, and adversarial input protections Background with large-scale, multi-tenant SaaS applications handling sensitive customer

injection, data exfiltration from LLM workflows, agent identity boundaries, and model risk Experience translating technical security concepts

injection attacks Conduct research on automated red-teaming, adversarial robustness, and other research that helps test for or find misuse

…including the agentic ones, where prompt injection, tool misuse, and data exfiltration

…large-scale agentic workflows for non-obvious prompt

injection, data leakage, and model supply chain risks Build guardrails for agents and AI tools, such as scoped permissions, sandboxing, and audit