Senior AI Security & Robustness Engineer

Overview:

Keysight is on the forefront of technology innovation, delivering breakthroughs and trusted insights in electronic design, simulation, prototyping, test, manufacturing, and optimization. Our ~15,000 employees create world-class solutions in communications, 5G, automotive, energy, quantum, aerospace, defense, and semiconductor markets for customers in over 100 countries. Learn more about what we do.

Our award-winning culture embraces a bold vision of where technology can take us and a passion for tackling challenging problems with industry-first solutions. We believe that when people feel a sense of belonging, they can be more creative, innovative, and thrive at all points in their careers.

About Keysight AI Labs

Keysight’s AI Labs is a global R&D group pioneering the integration of machine learning, generative AI into Keysight’s test, measurement, and design solutions. Our mission is to transform how engineers design, simulate, and validate advanced systems- from 6G and semiconductors to quantum and automotive - by embedding AI throughout our workflows.

About the AI Team

Join Keysight's central AI Hub in the heart of Barcelona. We are expanding our newly formed AI Team. As part of this growing team, you will join a vibrant, cross-functional environment that brings together experts in ML engineering, data science, physics-informed modeling, and software development. You’ll work closely with domain experts across RF, EM, circuit design, and test & measurement to accelerate scientific innovation through AI.

About the Role

We are seeking a Senior ML Security & Robustness Engineer who will lead the design and deployment of secure and resilient ML systems. This is a hands-on, research-informed engineering role focused on adversarial robustness, secure training, and model lifecycle security across diverse deployment targets, on-device, hybrid, edge, and cloud.

You will collaborate with applied researchers, data scientists, and infrastructure teams to design ML security solutions that scale from lab prototypes to enterprise-grade deployments.

Responsibilities:

This is a hands-on and high-impact role, blending applied research and production engineering:

Design, test, and deploy adversarial defenses for ML models across varied deployment architectures (edge, hybrid, cloud)

Own robustness evaluation pipelines, red-teaming, and model penetration testing

Secure ML artifacts via fingerprinting, obfuscation, and model watermarking

Implement privacy-preserving learning techniques (e.g., FL, DP-SGD)

Contribute to threat modeling and secure ML lifecycle governance

Develop and maintain tooling for continuous robustness testing and secure MLOps workflows

Collaborate with research and product teams to transition prototype defenses into production

Publish and communicate findings internally and externally when appropriate

Qualifications:

Required Qualifications

Education: Master’s or PhD in Computer Science, Electrical Engineering, Applied Mathematics, Cybersecurity, or related field.

ML/DL Foundations: Deep understanding of neural networks, optimization, and statistical learning theory.

Adversarial ML Expertise: Proven experience with model attacks, defenses, and robustness evaluation.

Secure Deployment: Experience deploying hardened ML models to embedded or resource-constrained environments.

Secure ML Lifecycle: Familiarity with secure ML lifecycle management, threat modeling, and ML governance frameworks.

Model IP Protection: Hands-on experience with model watermarking, fingerprinting, and secure model storage.

Frameworks & Tools: Strong skills in PyTorch (preferred) or TensorFlow; familiarity with IBM ART, CleverHans, or similar security libraries.

Privacy-Preserving ML: Experience with DP-SGD

Strong communication and cross-functional collaboration skills in English

Desired Qualifications

Experience with FL frameworks (e.g., Flower, OpenFL)

Familiarity with cryptographic principles and secure computation techniques

MLOps tooling experience (MLflow, W&B, CI/CD)

Publications in top AI and/or security venues (NeurIPS, ICML, AAAI, IEEE S&P, USENIX, ACM CCS, etc.)

Contributions to open-source ML security projects