Feras Al-kassar is an AI security researcher with 10 years' experience at the intersection of LLMs, agents, and static analysis, currently driving threat research at Sonar. He holds a Ph.D. in Security from Sorbonne and a strong publication record (NDSS, Usenix, EuroS&PW) exploring practical weaknesses in web apps and ML systems, and has multiple published CVEs in open source. His work spans prompt injection, RAG poisoning, agentic-system risks, and benchmarking ML guards, informed by prior roles building advanced static scanners and privacy compliance analyses. Comfortable in several programming languages and ML frameworks, he blends deep research rigor with hands-on engineering—e.g., developing transformations to improve static analysis coverage and applying differential privacy to text anonymization. Based in Geneva, he pairs academic depth with practical impact, uniquely bridging formal security testing and emerging LLM threat models.
10 years of coding experience
2 years of employment as a software developer
Master’s Degree, Machine Learning and Data Mining, Master’s Degree, Machine Learning and Data Mining at Université Jean Monnet Saint-Etienne
Master's degree, Advanced Data Analysis, Master's degree, Advanced Data Analysis at Leiden University
Bachelor’s Degree, Artificial Intelligence, Bachelor’s Degree, Artificial Intelligence at Damascus University
PhD, Advanced Security Testing of modern Web Applications, PhD, Advanced Security Testing of modern Web Applications at Sorbonne University
Community-based GPL-licensed network monitoring system
Contributions:10 pushes, 1 branch in 7 months
snmpcommunity-basedlicensedgplnetwork-monitoring
Find and Hire Top DevelopersWe’ve analyzed the programming source code of over 60 million software developers on GitHub and scored them by 50,000 skills. Sign-up on Prog,AI to search for software developers.