Lenovo Digital Trust Lab seeks for a talented and forward-thinking Security-AI Researcher to join our cutting-edge research team. This role will directly support our Hybrid AI initiative as well as our Device, Infrastructure, and Services security programs, focusing on advancing security, privacy, and trust through innovative research and applied AI.

As a core member of our R&D effort, you will explore the intersection of cybersecurity and artificial intelligence—identifying and mitigating emerging threats, designing trustworthy AI systems, and driving new ideas from concept to real-world impact.

Job Responsibilities:

• Conduct advanced research at the intersection of cybersecurity, privacy, trust, and AI/data science.
• Support both the hybrid AI and device/infrastructure/service security initiatives by identifying key risks and proposing intelligent solutions.
• Investigate and model AI-driven threats (e.g., adversarial machine learning, data poisoning, model extraction) and develop defense mechanisms.
• Contribute to the design of secure and trustworthy AI systems embedded within products and infrastructure.
• Collaborate with other researchers, engineers, and product teams to transform research outcomes into practical capabilities.
• Drive ideation, rapid prototyping, and technical innovation across the security-AI landscape.
• Publish and present impactful findings (internally or externally), staying at the forefront of academic and industry advancements

Minimum Requirements:

• M.Sc. in Computer Science, Cybersecurity, Data Science, or a related technical field.
• Proven research experience in cybersecurity, privacy, and trust, with a deep understanding of threat models, attack surfaces, and defense mechanisms.
• Strong foundation in AI and data science, including machine learning theory, and applied AI techniques.
• Hands-on experience in developing or evaluating secure AI systems, adversarial robustness, or privacy-preserving ML.
• Demonstrated ability to ideate, innovate, and prototype new solutions—evidenced by patents, publications, or successful R&D projects.
• Excellent analytical, communication, and collaboration skills.

Preferred Requirements:

• PhD in a relevant field or equivalent research experience in an industrial or academic setting.
• Experience working with hybrid AI architecture (agentic, multi-agent) or integrating AI into embedded systems/devices.
• Familiarity with secure infrastructure, cloud platforms, or trusted execution environments.
• Track record of peer-reviewed publications, patents, or contributions to open-source security/AI tools.
• Experience working in a multidisciplinary team with product, engineering, and security stakeholders.