AI Security Research Engineer - Architecture Team

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

Lenovo Digital Trust Lab is hiring an AI Security Research Engineer to join the Lab's Architecture Team. In this hands-on technical role, you will research new domains to map the Lab's solutions across the AI security landscape, translate emerging concepts into working proofs of concept, and drive zero-to-one development of new projects. You will also contribute to the unified architecture of the Lab's underlying technologies, building the shared foundations that the Lab's research groups rely on.

Job Responsibilities:

• Research new domains at the intersection of cybersecurity and AI, and map the Lab's solutions across the AI security landscape to identify gaps, overlaps, and new opportunities.
• Track academic research, open-source projects, emerging startups, and frontier model capabilities, and translate emerging concepts into concrete technical proposals.
• Turn emerging concepts into working proofs of concept (PoCs) quickly, to validate ideas and assess technical feasibility.
• Drive zero-to-one development of new Lab projects, taking validated PoCs to a first working version and handing them off to the research and engineering teams.
• Contribute to the unified architecture of the Lab's underlying technologies, designing shared frameworks and reusable components (e.g., agent infrastructure, evaluation harnesses, data pipelines, security tooling) used across research groups.
• Define technical standards and best practices for building secure, scalable AI and agent-based systems across the Lab. 
• Share findings through design reviews, technical write-ups, and, where relevant, external publications and talks.

Minimum Requirements:

• BSc in Computer Science, Software Engineering, or equivalent practical experience.
• 5+ years of hands-on software engineering experience, including at least 2 years in cybersecurity (security engineering, security research, or security product development).
• Software Engineering & Architecture: strong hands-on skills in
• Extensive hands-on software development: designing, writing, and shipping production-quality code in at least one of the following languages: Python, Go, TypeScript, Rust, or Java.
• Designing modular, scalable systems and shared platforms consumed by multiple teams, with clean APIs, testing, and documentation.
• AI / Agent Engineering: strong domain expertise and hands-on experience in
• Deep understanding of LLMs and autonomous agent architectures: planning, tool use, multi-step reasoning, memory, and retrieval (RAG).
• Solid knowledge of the agentic ecosystem, including MCP (Model Context Protocol), agent orchestration frameworks (e.g., LangChain/LangGraph, CrewAI),and frontier model capabilities.
• Hands-on experience building LLM-based applications or agent prototypes.
• Security Foundations: solid background in one or more of application security, threat modeling, vulnerability research, cloud security, or detection engineering.
• AI Security: familiarity with AI and agent threats such as prompt injection, jailbreaks, data and model poisoning, tool misuse, and AI supply-chain risk, and with frameworks such as OWASP Top 10 for LLM Applications and MITRE ATLAS.
• Research Skills: ability to explore ambiguous problems, read and apply academic papers, design experiments, and evaluate results critically.
• Fast-prototyping mindset, strong ownership, and clear communication with technical and non-technical audiences across groups.

Advanced Requirements:

• MSc in Computer Science, Cybersecurity, or a related technical field.
• Previous experience on an architecture, platform, or core-infrastructure team supporting multiple R&D groups.
• Experience driving zero-to-one projects in a research lab, startup, or innovation group, from PoC to a first working version.
• Hands-on experience building technical AI security products, from defining capabilities and architecture through delivery to customers.