Skip to content
MVPeople Group Logo
MVPeopleGroup
AI & LLM Security

Senior Security Engineer - AI

AmsterdamPermanentHybridSeniortech-saas

About the assignment

A leading organisation in tech-saas is scaling its AI capabilities and needs security built in from day one. You secure machine learning workflows, LLM deployments, and AI infrastructure across cloud environments. Your work prevents data poisoning, model theft, prompt injection attacks, and ensures AI systems comply with emerging regulations like the AI Act.

You're not firefighting—you're architecting security into AI from design phase onwards. You collaborate with ML engineers, data teams, and compliance to embed security without slowing innovation.

Your responsibilities

  • Design security architectures for machine learning pipelines and model governance frameworks
  • Implement controls against adversarial attacks, data poisoning, and model extraction threats
  • Monitor and secure large language model (LLM) deployments and third-party AI services
  • Conduct threat modelling for AI/ML systems using MITRE ATLAS and AI-specific attack vectors
  • Build security testing frameworks for model validation and prompt injection detection
  • Establish data governance and access controls for training datasets and model artifacts
  • Advise on AI Act compliance, responsible AI principles, and ethical AI governance

Tech Stack & Tools

Platforms & Tooling

Hugging FaceMLflowTensorFlow SecurityPyTorchWeights & BiasesAzure MLSageMaker

Frameworks & Standards

MITRE ATLASOWASP Top 10 for LLMsNIST AI RMFAI ActResponsible AI principles

Cloud & Infrastructure

AWS (SageMaker, GuardDuty)Azure (ML, Defender for Cloud)GCP (Vertex AI, SCC)

Methodologies

Threat modelling for ML systemsAdversarial robustness testingModel validation and verificationSecure SDLC for AI

Certifications (preferred)

CCSK (Cloud Security Knowledge)AWS Security SpecialtyAZ-500CISSP

Must-haves

  • 5+ years security engineering experience with minimum 2 years in AI/ML security
  • Hands-on experience securing machine learning platforms and model governance
  • Strong understanding of AI/ML attack vectors (adversarial attacks, data poisoning, model extraction)
  • Proficiency with cloud security (AWS, Azure, or GCP) and ML frameworks
  • Experience designing security controls for data pipelines and model lifecycle management

Nice-to-haves

  • Threat modelling experience using MITRE ATLAS or similar AI-specific frameworks
  • Familiarity with LLM security, prompt injection testing, and generative AI risks
  • Background in privacy engineering or compliance (GDPR, AI Act)

What we offer

  • Shape security strategy for cutting-edge AI systems before they scale
  • Work with ML and data teams—bridge the gap between security and innovation
  • Influence responsible AI practices across the organisation
  • Access to latest AI security research and tools
  • Continuous learning in a rapidly evolving field
  • Personal guidance from a dedicated MVPeople consultant who knows your niche

The process

1

Introduction

Phone call with your MVPeople consultant (within 24 hours)

2

Match & Brief

We discuss the assignment in detail and prepare you

3

Client meeting

Introduction to the client

4

Start

Contracting and onboarding

Details

Type

Permanent

Location

Amsterdam

Work model

Hybrid

Level

Senior

Industry

tech-saas

Posted

24 March 2026


Contact

Apply nowMore information
Apply now