Hiring nowAI application security and misuse defence

Model Weights Security Engineer

Also called AI Infrastructure Security Engineer

A Model Weights Security Engineer protects trained model weights and the training infrastructure around them from theft, including by well-resourced state actors. Losing weights means losing the company's core asset and control over how its models are used.

What they do

The work is hardening the systems where weights are trained, stored and served. That means designing access controls, isolating environments, and limiting who and what can move or copy weights. They build monitoring to spot unusual access or data movement. They run threat models against realistic attackers, including insiders and state-backed groups. They work with infrastructure and research teams so controls fit how models are actually built. They red team their own defences, investigate alerts, and lead response when something looks wrong. They also map work to a stated security target and report on the gaps.

What a strong hire delivers

In the first months, a strong hire delivers a clear threat model for weights and training systems, with the biggest gaps ranked and owned. They tighten access to weights and put in monitoring that catches odd copying or exfiltration. They agree a security target with leadership and a plan to reach it. They run at least one realistic attack exercise and fix what it finds. Research teams keep working without constant friction.

How you can tell they are good

Ask them to walk through how they would stop a trusted insider copying weights, then a state-level attacker. Strong people think in layers, name trade-offs, and say what they would detect rather than only prevent. Ask for a real incident or exercise they ran and what changed afterwards. Worry if they offer generic checklists or ignore how researchers actually work.

Why it is hard to fill

Very few people have protected assets of this kind against this class of attacker. Titles vary, and the work sits between infrastructure security, detection, insider risk and hardware. Many candidates are strong in one area but thin in the others. Clearance is often required, which shrinks the pool further. Frontier labs compete for the same small group, so searches take careful targeting and patience.

Where to find them

Look first at application security engineers, threat detection engineers and security researchers who have moved toward infrastructure. Others come from infrastructure security teams, insider-threat programmes and hardware security groups. Government and defence-adjacent security teams are a strong source, especially where clearance is held. Large cloud operators and security-heavy technology companies also produce people who have defended valuable assets under real attack.

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 a Model Weights Security Engineer

  1. Walk us through how you would threat model a training cluster where model weights are stored and moved.

    A strong answer names assets, attackers, entry points and trust boundaries, then ranks risks. It covers insiders and supply chain, not only outside attackers. Worry if it is a tool list with no prioritisation or reasoning.

  2. Describe a time you protected a high-value asset against a capable attacker. What did you build and what failed?

    Look for specific controls, honest failures and measurable change afterwards. Good candidates own mistakes and explain what they learned. Worry about vague claims, credit taken for team work, or no mention of detection.

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

Job description you can post

We build and train frontier-scale models, and our weights are our most valuable asset. We are hiring a Model Weights Security Engineer to protect them and the systems that produce them from theft, including by highly capable attackers. You will work closely with infrastructure and research teams.

What you will do

  • Threat model weights storage, training and serving systems
  • Design and enforce access controls and environment isolation
  • Build monitoring to detect unusual access and data movement
  • Run red team exercises against our own defences
  • Lead investigation and response for security incidents
  • Track progress against our security targets and report gaps
  • Advise research and infrastructure teams on secure design

What you will bring

  • Demonstrated work securing infrastructure holding high-value assets
  • Experience in threat detection, security research or application security
  • Ability to threat model against insiders and advanced attackers
  • Experience running or responding to real security incidents
  • Clear communication with engineers and researchers
  • Eligibility for security clearance where required

Nice to have

  • Experience with insider-threat programmes
  • Hardware security knowledge
  • Experience securing large compute clusters

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

Skills that matter

  • Security engineeringWorkingProtect systems, identities and sensitive assets
  • AI red teamingWorkingTest 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 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 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 a Model Weights 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.