
Senior AI Security Researcher- Remote
- תל אביב
- משרה קבועה
- משרה מלאה
- Researching novel prompt injection techniques, jailbreaks, adversarial abuse patterns, and vulnerabilities in agentic AI systems.
- Investigating new model behaviours agentic workflows, and tooling to uncover abuse and identify gaps in current defences.
- Working with data from large enterprise environments to analyse suspicious behaviours and continuously refine Akamai's protection mechanisms.
- Designing attack simulations and develop validation methodologies and tools to evaluate the safety and robustness of LLMs.
- Contributing to Akamai's leadership in AI security by publishing research and speaking at conferences.
- Working cross-functionally with data scientists, engineers, and product teams to bring research into real-world protection.
- Have 5+ years of experience in security research, with a focus on API, web, or cloud security.
- Have proven experience in AI security.
- Demonstrate a deep understanding of large language models and agentic AI systems.
- Have proven experience analysing large-scale data to extract insights, support research, and drive data-informed decisions.
- Have programming skills in Python, with the ability to build proof-of-concept tools, automations, and experimental frameworks.
- Have a background in penetration testing or offensive security techniques.
- Have problem-solving and creative thinking, with an ability to navigate ambiguity, drive investigations, and collaborate with teams.