Hiring nowAI application security and misuse defence

AI Security Engineer

Also called GenAI Security Engineer

An AI Security Engineer hardens the applications, interfaces and sensitive assets built around models. They find how attackers could misuse the product and fix it, so the company can ship AI features without exposing customers or data.

What they do

They map how a model-connected product can be attacked, then test it. That means threat modelling agents, tool calls, retrieval pipelines and user-facing interfaces. They write and run attacks such as prompt injection, data exfiltration and abuse of connected tools. They set up identity controls, sandboxes and logging so unauthorised use is limited and visible. They work with engineers to fix defects, rank them by impact and retest. They also help the team respond when something goes wrong, and keep a record of what was learned.

What a strong hire delivers

In the first months, a strong hire produces a clear threat model for the main AI product and a short list of ranked risks. They put tested controls in place for the highest-impact gaps, such as tool permissions, sandboxing and logging. They leave behind a repeatable attack test suite that engineers can run, and a working incident routine the team trusts.

How you can tell they are good

Ask them to walk through a threat model they built for a system where a model can call tools or read untrusted content. Good candidates name the assets, the trust boundaries and the attacks they actually tested. They explain which fixes worked and which failed. Be wary of people who only list known attack names without showing evidence of fixing anything.

Why it is hard to fill

The title is new and the background is mixed. Most good candidates come from application security, detection or research, then taught themselves how models fail. Few have shipped controls on a live AI product. Job titles rarely say what someone has done, so a recruiter has to read the work itself. Founders often ask for pure red teamers when they need someone who also fixes things.

Where to find them

Look at application security engineers, threat detection engineers and security researchers who have moved towards AI work. Some sit in product security teams at software companies. Others work in red teams, security consultancies or at model providers. Also check engineers who built agent features and became the person who worried about abuse. Public write-ups of attacks and fixes are a useful signal.

Indicative pay

Not enough published evidence yet to give a fair range for this role, which is common for work this new. We benchmark it for you as part of a search.

Interview questions for an AI Security Engineer

  1. Describe a threat model you built for a system where a model could call tools or read untrusted content.

    Strong answers name assets, trust boundaries and realistic attackers, then show which risks they tested and ranked. They should describe changes that followed. Worry if the answer is a generic list of attack names with no system detail.

  2. How would you reduce the damage if a prompt injection succeeds in one of our agents?

    Good answers assume the injection will sometimes work. They cover least privilege for tools, sandboxing, confirmation for risky actions, output controls and logging. Worry if the main defence offered is a better system prompt.

4 more questions, with what a strong answer covers, are in the Role Kit.

Job description you can post

We are building AI features that connect models to tools, data and customers. We need an AI Security Engineer to find how these systems could be attacked or misused, and to put tested controls in place. You will work closely with the engineers who build the product.

What you will do

  • Build and maintain threat models for AI applications, agents and their interfaces
  • Test for prompt injection, data leakage and misuse of connected tools
  • Design and implement access controls, sandboxing and logging
  • Create repeatable attack tests that run as the product changes
  • Work with engineers to fix high-impact defects and verify the fixes
  • Help the team respond to security incidents involving AI features

What you will bring

  • Demonstrated application security, threat detection or security research work
  • Experience threat modelling a system that includes a model or agent
  • Examples of vulnerabilities you found and got remediated
  • Working knowledge of identity, permissions and logging in production systems
  • Ability to write code and test harnesses
  • Clear written communication of risk to engineers and leaders

Nice to have

  • Experience with agent frameworks and tool or protocol integrations
  • Published research or write-ups on attacks against AI systems
  • Incident response experience on a live product

Free to use and adapt. If it saves you time, a link back to this page is appreciated.

Skills that matter

  • Security engineeringAdvancedProtect systems, identities and sensitive assets
  • AI red teamingAdvancedTest systems adversarially under authorisation
  • Tool and protocol integrationWorkingConnect models to external data and capabilities
  • Reliability and incident responseWorkingDetect failures, restore service and prevent recurrence

Other roles in aI application security and misuse defence

Hiring nowAI Red Team EngineerAn AI Red Team Engineer runs authorised attacks against model-connected systems to find weaknesses before real adversaries do. They give the company…Hiring nowAI Abuse Detection AnalystAn AI Abuse Detection Analyst spots unauthorised and harmful use of a company's models and products, then turns what they find into rules and cases…EmergingModel Supply Chain Security EngineerA Model Supply Chain Security Engineer protects model files, datasets and dependencies from tampering. They give the company confidence that what it…Hiring nowAgent Security EngineerAn Agent Security Engineer protects AI agents from prompt injection, data leaks and tool misuse. They let a company ship agents that act on real…Hiring nowModel Weights Security EngineerA Model Weights Security Engineer protects trained model weights and the training infrastructure around them from theft, including by well-resourced…Hiring nowAI Threat Intelligence AnalystAn AI Threat Intelligence Analyst tracks how threat actors use AI to attack, deceive and abuse systems, then turns what they find into detections…EmergingAgent Identity and Permissions ArchitectThis person designs how AI agents prove who they are and what they may do. They keep access narrow as agent numbers grow, so one compromised agent…Hiring nowAI Trust and Safety SpecialistAn AI Trust and Safety Specialist writes and enforces the rules for how a model-connected product can be used, and investigates misuse. They keep…

Related roles in other families

Hiring nowCybersecurity ML ScientistCyber defence and security operations AIA Cybersecurity ML Scientist builds and tests models that spot malicious activity in authorised security data. They keep detection useful as…Hiring nowAI Detection EngineerCyber defence and security operations AIAn AI Detection Engineer builds the detections that turn AI-derived signals into alerts a security team can trust. They cut noise, catch real…EmergingAI Security Operations EngineerCyber defence and security operations AIAn AI Security Operations Engineer builds constrained AI support for security triage and response. It lets a security team move faster on alerts and…EmergingDefensive AI Agent EvaluatorCyber defence and security operations AIA Defensive AI Agent Evaluator tests how AI agents behave inside security detection and response work, and shows where they fail. It matters because…

How we wrote this

Role definitions are our own editorial work, checked against occupational classifications, standards, research and employer pages. Titles vary by company, and this is a description of the work, not a job advert.

← AI application security and misuse defenceAll new job families

Start a search

Hiring an AI Security Engineer?

Tell us the work. We find the people already doing it, whatever their job title says, and you meet them already interviewed for your role.