Hiring nowAI application security and misuse defence

AI Red Team Engineer

Also called LLM Red Teamer · AI Red Teamer · Adversarial Tester · Jailbreak Specialist

An AI Red Team Engineer runs authorised attacks against model-connected systems to find weaknesses before real adversaries do. They give the company evidence of what can break, how badly, and whether the fix held.

What they do

They plan and run authorised adversarial tests against products that connect models to data, tools and users. They try prompt injection through documents, web content and tool outputs. They probe agent boundaries: what an agent can reach, what it can be talked into doing, and where permissions leak. They build test harnesses and sandboxes so attacks can be replayed. They write up each finding with steps to reproduce, a severity rating and a suggested mitigation. They sit with engineers while fixes are made, then retest. They also read logs to see whether an attack would have been noticed.

What a strong hire delivers

In the first months, a strong hire maps where the product trusts model output or outside content, and tests those points first. They leave behind a reproducible attack suite that engineers can run themselves. They deliver clear, severity-ranked findings, not long lists of curiosities. Validated issues get fixed and retested, with evidence that the fix holds. Logging and detection gaps are named and closed. Teams start to consider abuse earlier in design.

How you can tell they are good

Ask them to walk through a real finding from start to finish. Look for the exact steps, how they judged severity, and how they confirmed the fix. Give them a simple agent design and ask where they would attack first. Strong people talk about boundaries, permissions and impact. Be wary of those who only show clever jailbreak prompts with no reproducibility or consideration of real harm.

Why it is hard to fill

Titles vary widely, so searching by title misses most of the good people. The work needs classic security discipline, creative attacker thinking and enough domain knowledge to judge real harm. Few people hold all three. Many security engineers have never tested agents, and many model-focused people lack rigour in reporting. Labs, enterprises and public safety institutes are all competing for the same small group.

Where to find them

Most come from application security, penetration testing, threat detection and security research. Some have worked on abuse and trust teams, or in vulnerability research. A smaller group has moved from machine learning evaluation into adversarial work. Look at labs, large enterprises with active security teams, security consultancies, and public bodies that test AI systems. Strong candidates often have written-up research or disclosed findings.

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 Red Team Engineer

  1. Describe a prompt injection finding you reproduced. How did you demonstrate impact and rate its severity?

    A strong answer gives exact steps, the data or action at risk, and a reasoned severity rating. It shows how someone else could reproduce it. Worry if the story is about a clever prompt with no real consequence.

  2. How would you test the boundaries of an agent that can send email and read internal documents?

    Look for mapping tools, permissions and data flows first. They should test indirect injection, privilege escalation and data exfiltration. Worry if they only try direct jailbreaks against the chat box.

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

Job description you can post

We build products that connect models to data, tools and users. We need an AI Red Team Engineer to attack them, with authorisation, before anyone else does. You will find weaknesses, prove them, and help us fix them and check the fixes hold.

What you will do

  • Plan and run authorised adversarial tests of model-connected systems
  • Test for prompt injection and unsafe agent behaviour across tools and data sources
  • Build repeatable test harnesses and sandboxes
  • Write reproducible findings with severity and suggested mitigations
  • Retest fixes and record the evidence
  • Work with engineers to improve logging and detection
  • Share what you learn so design choices improve

What you will bring

  • Demonstrated security testing of real applications or systems
  • Worked examples of finding and reporting vulnerabilities clearly
  • Hands-on experience probing LLM applications or agents
  • Comfortable writing code and scripts for test tooling
  • Sound judgement on severity and real-world harm
  • Clear written communication with engineers
  • Careful, ethical approach to authorised testing

Nice to have

  • Published research or disclosed findings
  • Experience with identity and access systems
  • Background in incident response or threat detection
  • Domain knowledge of a high-risk sector

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 Security EngineerAn AI Security Engineer hardens the applications, interfaces and sensitive assets built around models. They find how attackers could misuse the…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 Red Team 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.