Lenovo – Sr. Researcher, Research Lead – Hybrid AI Security
Lenovo’s Digital Trust Lab is hiring a Research Lead to lead Hybrid AI Security in Petach Tikva. You’ll define the future of LLM and multi-agent system security by bridging theory, implementation, and global collaboration.
Key Responsibilities:
– Lead research on LLM security, multi-agent trust, prompt injection, and sandboxing
– Drive innovation in areas such as misuse prevention and secure orchestration
– Collaborate with engineers and product teams to translate findings into real applications
– Represent Lenovo in academia and industry via talks, publications, and patents
What You Need:
– MSc or PhD in AI, ML, or Cybersecurity
– 8+ years in cybersecurity, 5+ years in deep learning or LLMs
– Hands-on with LangChain, AutoGen, and modern AI infra
– Proven impact through papers, systems, or thought leadership
Preferred:
– Experience in red teaming, ethics in AI, or policy/standardization
– Deep knowledge of orchestration layers, secure APIs, and agent coordination frameworks