EmergingAI application security and misuse defence

Model Supply Chain Security Engineer

Also called ML Supply Chain Security Engineer

A Model Supply Chain Security Engineer protects model files, datasets and dependencies from tampering. They give the company confidence that what it trains, ships and serves is what it meant to.

What they do

They map how models, weights, datasets and packages move from source to production, then put controls on each step. That means signing artefacts, checking them before use, reviewing new dependencies and tightening who can change what. They write tests that try to slip a tampered file or a poisoned package through the pipeline. They set up logging so unexpected changes are noticed fast. They work with ML engineers, platform teams and infrastructure staff, and they run sandboxes for inspecting untrusted artefacts. When something looks wrong, they help investigate and contain it.

What a strong hire delivers

In the first months, a strong hire produces a clear map of where artefacts and dependencies come from and who can alter them. They put signing and verification on the most critical model and data paths. They build repeatable tests that show whether tampering would be caught. They tighten access to storage and registries, and they leave the team with logging and alerts that someone actually reads and understands.

How you can tell they are good

Ask them to walk through a pipeline they secured and show where tampering could have happened. Good candidates name specific attack paths, such as swapped weights, poisoned datasets or malicious packages, and explain the control and the test for each. They can say what they chose not to lock down and why. Be wary of generic security talk with no sign of the ML workflow.

Why it is hard to fill

Almost nobody carries this title yet. The work usually sits inside application security, platform or ML infrastructure roles, so CVs rarely say it. Candidates tend to know either security or ML pipelines well, seldom both. Those who have done it often did so as part of a wider job. We search by what people have built, not by their title, and we expect to coach some hires on the ML side.

Where to find them

Look at application security engineers who have worked on build pipelines and package integrity. Threat detection and security research backgrounds also fit, especially if they have studied malicious packages or tampered files. Some come from ML platform or infrastructure teams that took on security duties. Frontier labs, model providers, security vendors and larger AI product companies are the most likely places to find them.

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 Supply Chain Security Engineer

  1. Describe how you would verify that a model file in production is the one your team approved.

    Covers signing at the point of approval, verification at load time, a trusted registry and access limits on who can publish. Look for attention to key management. Worry if the answer stops at checksums with no thought about who controls them.

  2. Tell me about a time you found or prevented tampering or a malicious dependency. What did you do?

    A real, specific account: how it was detected, what was contained and what changed afterwards. Strong answers are honest about gaps. Worry about vague stories, or ones where the candidate only followed an alert someone else raised.

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

Job description you can post

We are hiring a Model Supply Chain Security Engineer to protect the models, datasets and dependencies our products rely on. You will make sure what we train, ship and serve has not been tampered with, and that we would know quickly if it had.

What you will do

  • Map how model artefacts, datasets and packages move from source to production
  • Introduce artefact signing and verification across key pipelines
  • Review new dependencies and pretrained models before they are adopted
  • Build tests that try to pass tampered artefacts through our controls
  • Tighten access to registries, storage and build systems
  • Set up logging and alerts for unauthorised changes
  • Help investigate and contain suspected tampering

What you will bring

  • Demonstrated work securing build, release or data pipelines
  • Hands-on experience with signing, provenance or integrity checking
  • Experience reviewing dependencies for malicious or risky behaviour
  • Working knowledge of identity and access controls
  • Ability to write test harnesses and automation
  • Clear communication with research and engineering colleagues

Nice to have

  • Experience with ML training or serving workflows
  • Background in red teaming or threat detection
  • Experience running sandboxes for untrusted code or files

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 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…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 a Model Supply Chain 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.