Security Engineer, Model Threats Red-team our own products before anyone else does. Assurance USA / Remote →

Zitrino; Northern (KY); Hybrid; USD 100,000 - 180,000; Full time

Job summary

Zitrino is seeking a security-focused professional to red-team our own products and validate defenses before client deployments in the United States. You will work with engineering to design mitigations that survive the next model swap and own threat modelling for new product surfaces.

You will support client security reviews with honest findings and clear remediation, and communicate findings so engineers can fix them without a meeting.

Qualifications

• Offensive security testing experience for applications or cloud.
• Engineering mindset—you build the tooling you need.
• Understanding of retrieval, tool calls and agent loops.
• Findings written so engineers can fix them without a meeting.

Responsibilities

• Support client security reviews with honest findings and clear remediation.
• Own threat modelling for new product surfaces.
• Work with engineering on mitigations that survive the next model swap.
• Red-team our own products before client environments.

Skills

Offensive security

Cloud security testing

LLM systems

Threat modelling

Job description

Red-team our own products before anyone else does. Prompt injection, tool abuse, data exfiltration through retrieval: find it here, not in a client environment.

Work with engineering on mitigations that survive the next model swap.

Own threat modelling for new product surfaces.

Support client security reviews with honest findings and clear remediation.

What we are looking for

Offensive background Application or cloud security testing experience, ideally with LLM systems.

Engineering You write the tooling you need rather than filing a ticket for it.

AI systems Understanding of how retrieval, tool calling and agent loops actually fail.

Reporting Findings written so an engineer can fix them without a meeting.