Applied AI Security Researcher - AI for Security Team

Lenovo Digital Trust Lab is hiring an Applied AI Security Researcher to lead hands-on research in the AI for Security domain. You will explore, design, and build next-generation AI agents that secure the software development lifecycle, shifting security left into how code is designed, written, reviewed, and shipped in the era of AI-powered development. You will work directly with frontier models and take ideas from research to working technology. Candidate must be willing to work onsite in our Tel-Aviv, Israel office. Job Responsibilities: Lead hands-on research in the AI for Security domain, defining research directions for how AI agents can secure the AI-powered software development lifecycle. Research the industry landscape, including academic work, emerging startups, open-source projects, and frontier model capabilities, and turn insights into concrete research bets and roadmap. Explore and prototype new solutions that shift security left, using AI agents for secure design, code review, vulnerability discovery, and automated remediation across the SDLC, including securing code produced by AI coding assistants. Design and develop novel technologies and agent-based security capabilities end-to-end, from proof of concept to production-ready solutions delivered with the engineering team. Build benchmarks, datasets, and evaluation methods that measure how well AI agents perform on real-world security tasks, and share findings through publications, talks, and mentoring. Minimum

BSc in Computer Science or equivalent practical experience. 5+ years of hands-on experience in security research or security engineering, with a track record of original, impactful work (e.g., CVEs, conference talks, open-source tools). AI / Agent Engineering: extensive hands-on experience in: Designing, building, and shipping autonomous AI agents (planning, tool use, multi-step reasoning, error recovery). Applying AI agents and LLMs to security problems, translating expert security workflows into intelligent, multi-step decision systems. Working with frontier reasoning models: prompting, retrieval (RAG), context engineering, and grounding techniques. Agent orchestration frameworks (LangChain, CrewAI, or custom planners/executors) and the agentic ecosystem: MCP (Model Context Protocol), tooling, memory systems, and skills. Building evaluations for non-deterministic systems: datasets, benchmarks, and regression suites. SDLC Security: deep foundations in: Application security across the SDLC: secure design, threat modeling, secure code review, and shift-left practices. Vulnerability research and exploitation techniques across modern web apps, APIs, and enterprise systems. AI-powered development workflows and coding assistants (Claude Code, Cursor, GitHub Copilot, and similar) and the security risks they introduce. Strong software engineering skills: production-quality Python and one other language, and the ability to take research prototypes toward production. Ability to lead ambiguous research problems independently and communicate findings clearly to technical and non-technical audiences. Advanced Requirements: M.Sc in Computer Science, Cybersecurity, or a related technical field. Previous experience in applied research roles, taking research from idea to working technology. Code security analysis (SAST, DAST, SCA, secret scanning, fuzzing) and integrating it into CI/CD and developer workflows. Software supply-chain security: dependency and package risk, SBOMs, and build integrity. What we offer: Disability Insurance Health Insurance Pension Fund Retirement Fund Study Fund Meal Allowance Employee Referral Bonus Employee Assistance Program 10% discount on Lenovo products Internal e-learning platform Please note that the office is located at 121 Menachem Begin Road, Tel Aviv, 61st floor, in the POINT office complex. As per our office policy, you will be required to visit the site at least 3 times a week. #DTL #LI-Hybrid