Frontier Tech Prompt Injection Jobs

…work on LLM/agent threat modeling, prompt injection defenses, or AI red teaming.

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

…features and internal agents, covering prompt injection, tool and permission scoping for autonomous agents, PHI leakage, de-identification

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

…application security, agentic workflows, MCPs, prompt injection, autonomous coding agents, or AI platform security

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

injection and off-scope use.

…risks: data poisoning, model extraction, prompt

injection and off-scope use.

…and usability, including protections against prompt injection, data leakage, and unauthorized actions.

injection prevention, data isolation).

injection prevention, data isolation).