AI/ML Security Engineer

Blackfluo.ai; Paris; Sur place; EUR 70 000 - 90 000; Plein temps

Résumé du poste

A cybersecurity-focused AI company is seeking an AI/ML Security Engineer to enhance AI systems' protection against adversarial threats. The role involves using AI techniques for threat detection, operationalizing models, and collaborating with security teams. The ideal candidate has extensive experience in cybersecurity, knowledge of machine learning frameworks, and a strong understanding of adversarial attacks. This position is based in Paris, France.

Qualifications

• 6+ years experience in cybersecurity and/or applied machine learning.
• Hands-on experience with ML frameworks and data pipelines.
• Understanding of adversarial ML concepts and experience applying strategies.

Responsabilités

• Develop and operationalize AI/ML models for anomaly detection.
• Analyze data to detect patterns indicative of cyber threats.
• Implement controls to protect AI pipelines from manipulation.

Connaissances

Cybersecurity principles

Threat modeling

Machine learning frameworks

Programming proficiency in Python

Data analysis libraries

Formation

Advanced degree in Computer Science, Cybersecurity, or related field

Outils

TensorFlow

PyTorch

Scikit-learn

Description du poste

Leveraging AI to enhance cybersecurity while protecting machine learning systems from adversarial threats

Position Overview
We are seeking an innovative AI/ML Security Engineer who combines deep knowledge of cybersecurity with experience in artificial intelligence and machine learning. This cross-disciplinary role focuses on two key areas: using AI/ML techniques to detect and respond to threats more effectively, and ensuring the security of AI models against adversarial attacks such as data poisoning, model inversion, and evasion techniques.

You will collaborate across security operations, data science, and DevSecOps teams to operationalize intelligent threat detection and protect critical AI systems from emerging threats.

Key Responsibilities

AI for Cybersecurity

• Develop and operationalize AI/ML models for anomaly detection , threat intelligence analysis , and automated incident response
• Analyze large volumes of log and telemetry data to detect patterns indicative of cyber threats
• Integrate ML-driven detection with SIEM, SOAR, and XDR platforms to improve automation and speed of response

Securing AI/ML Systems

• Implement controls to protect AI pipelines from manipulation, including input validation, data sanitization, and model monitoring
• Identify and mitigate threats such as data poisoning , model inversion , adversarial examples , and membership inference
• Evaluate ML models for robustness, fairness, and explainability from a security perspective

Governance & Collaboration

• Work with data scientists and MLOps teams to embed security into the AI development lifecycle
• Document AI system threat models and design risk mitigation strategies
• Stay updated on AI security research, adversarial ML techniques, and emerging regulatory considerations

Required Qualifications

• 6+ years experience in cybersecurity and/or applied machine learning
• Strong knowledge of cybersecurity principles , threat modeling, and security architecture
• Hands-on experience with ML frameworks (e.g., TensorFlow, PyTorch, Scikit-learn ) and data pipelines
• Understanding of adversarial ML concepts and experience applying mitigation strategies
• Programming proficiency in Python, and experience with data analysis libraries

Preferred Qualifications

• Advanced degree in Computer Science, Cybersecurity, Machine Learning, or related field
• Security certifications (e.g., CISSP, OSCP, or ML-specific credentials)
• Experience with ML model deployment in secure environments (e.g., MLOps, containerization)
• Familiarity with AI governance, ethics, and security standards (e.g., NIST AI RMF, ISO/IEC 23894)
• Contributions to AI security research, open-source tools, or community knowledge