Researcher, App Sec Expert - Edge Team

We are Lenovo. We do what we say. We own what we do. We WOW our customers.

Lenovo is a US$83 billion revenue global technology powerhouse, ranked #153 in the Fortune Global 500, and serving millions of customers every day in 180 markets. Focused on a bold vision to deliver Smarter Technology for All, Lenovo has built on its success as the world’s largest PC company with a full-stack portfolio of AI-enabled, AI-ready, and AI-optimized devices (PCs, workstations, smartphones, tablets), infrastructure (server, storage, edge, high performance computing and software defined infrastructure), software, solutions, and services. Lenovo’s continued investment in world-changing innovation is building a more equitable, trustworthy, and smarter future for everyone, everywhere. Lenovo is listed on the Hong Kong stock exchange under Lenovo Group Limited (HKSE: 992) (ADR: LNVGY).

This transformation together with Lenovo’s world-changing innovation is building a more inclusive, trustworthy, and smarter future for everyone, everywhere. To find out more visit www.lenovo.com, and read about the latest news via our StoryHub.

Candidate must be willing to work onsite three days a week in our Tel-Aviv, Israel office.

Lenovo Digital Trust Lab is seeking a hands-on AI Security Researcher to join our AI Security team. This role focuses on researching and developing new capabilities for our AI Controls Platform and bringing them into production across Lenovo’s AI ecosystem.

You will work at the intersection of AI security, software engineering, agentic AI, machine learning, and cybersecurity, investigating new attack techniques and vulnerabilities, developing detection and mitigation approaches, and building prototypes that evolve into robust production controls.

The ideal candidate combines strong research and analytical skills with hands-on implementation experience. Experience in AI/ML, security, adversarial machine learning, LLM security, AI red teaming, or AI agents is a strong advantage.

Job Responsibilities

• Research emerging and evolving AI security threats, vulnerabilities, and attack techniques across LLMs, AI applications, AI agents, and AI systems.
• Research security challenges in agentic AI, including tool/function calling, agent orchestration, MCP, memory and context, and multi-agent workflows.
• Identify and investigate novel security risks across the AI lifecycle, including data, models, inputs, outputs, tools, agents, and AI systems.
• Design and curate datasets, benchmarks, experiments, evaluations, and empirical studies to investigate AI security problems and validate proposed approaches.
• Develop novel detection, mitigation, and defensive techniques for AI security, safety, privacy, and robustness, across different modalities.
• Translate research findings into practical security controls and capabilities for Lenovo AI applications and the AI Controls Platform.
• Collaborate closely with AI security engineers, software engineers, data scientists, and product teams to transition promising research from experimentation to production.
• Contribute to technical reports, research papers, patents, internal research publications, and other research artifacts.
  
  

• 5+ years of professional or research experience in AI/ML, cybersecurity, AI security, software engineering, or a related technical field.
• MSc or PhD in computer science, cybersecurity, machine learning, or a related field.
• Strong understanding of machine learning and modern AI systems, with hands-on experience developing, analyzing, or evaluating models, AI applications, and agents.
• Strong programming skills in Python and/or another modern programming language such as Java, Kotlin, C++, Rust, or Go.
• Experience designing and conducting technical experiments, evaluations, or research projects, including defining methodologies and analyzing results.
• Strong software engineering skills, with experience building reliable, maintainable, and production-quality software.
• Ability to independently investigate complex and ambiguous technical problems, formulate hypotheses, and design, implement, and evaluate solutions.
• Strong ability to communicate technical findings through clear documentation and presentations, and collaborate effectively across research, engineering, and security teams.
  
  

• Opportunities for career advancement and personal growth
• Access to a diverse range of training programs to sharpen your skills
• Performance-based rewards that celebrate your achievements
• Enjoy the best of both worlds with our hybrid setup: 3 days connecting with the team in the office and 2 days working from the comfort of your home