Advisory AI Security Researcher

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 Applied AI Security Researcher to join our AI Security team. This role focuses on advancing our AI security monitoring capabilities, developing methods to detect attacks, misuse, and anomalous behavior across AI applications and agentic workflows. 

You will lead applied research that turns emerging threats and runtime telemetry into actionable detections and investigation context. Working closely with security researchers, data scientists, engineers, and security operations teams, you will take detection methods from research and prototyping through validation and production integration. 

The ideal candidate combines security research experience with strong engineering skills, an understanding of AI systems, and an interest in detecting threats across complex, multi-step interactions. 

Job Responsibilities: 

• Lead applied research into emerging AI threats, defining monitoring use cases and detection methods. 

• Develop detections for attacks and misuse across AI interactions, agentic workflows, tools, and memory. 

• Define telemetry requirements and correlate signals into actionable alerts and investigation context. 

• Validate detection coverage and effectiveness, reducing false positives. 

• Partner with engineers and SOC teams to deploy detections and improve them using operational feedback. 

Minimum Requirements: 

• 5+ years of experience in security research, threat detection, detection engineering, or applied AI/ML research, with demonstrated ownership of research initiatives. 

• BSc or MSc in computer science or a related field, or equivalent practical experience. 

• Strong Python skills for research prototyping and data analysis. 

• Practical experience investigating attacks, developing detections, or analyzing security telemetry. 

• Understanding of LLMs and agentic applications, including tools, retrieval, and memory. 

• Strong experimental, analytical, and collaboration skills, with the ability to translate research into practical capabilities. 

Preferred Requirements 

Experience in one or more of the following: 

• AI Security: Prompt injection, agent misuse, data exfiltration, AI red teaming, or adversarial ML. 

• Detection Methods: Behavioral analysis, anomaly detection, signal correlation, or ML/LLM-based detection. 

• Agentic AI: Agent frameworks, MCP, tool calling, or multi-agent workflows. 

• Security Operations: Threat hunting, incident investigation, SIEM/SOAR, or SOC integration. 

• Research to Production: Deploying detection prototypes and refining them using operational telemetry and feedback.