Oren Rachmil is a Senior AI Researcher at Fujitsu Research of Europe, working on the safety, evaluation, and security of large language model systems. His recent research focuses on analyzing gaps in open-source LLM vulnerability scanners, understanding evaluator reliability, and advancing practical methodologies for assessing model robustness and policy compliance in real-world deployments. He has contributed to comparative studies of LLM security tooling and to monitoring and attribution methods for generative models, bridging AI safety, transparency, and deployment concerns.
linkedin.com/in/oren-rachmil-16b757251/
