Karol Piekarski is a Lead DevSecOps Engineer working in Financial Services, where he oversees the security posture of complex enterprise systems. Joining via the acquisition of insurtech startup Gabi in 2021, Karol played a key technical role in the transition, combining startup agility with enterprise rigor.

Recognized as a Wiz MVP for his contributions to the cloud security community and an active contributor to the Cloud Security Alliance (CSA), Karol holds comprehensive credentials including CCSP, CKA, and AWS Security & DevOps Professional. His daily focus spans the full defensive stack, from CSPM, KSPM, and CIEM to the cutting edge of CDR and AISPM. Recently, Karol has focused on adapting these mature DevSecOps methodologies to the emerging "wild west" of Generative AI, researching how to secure open-source LLMs against injection and extraction attacks.

Presentations

23x

Red Teaming the Robot: Practical Open Source Security for LLMs

As organizations rapidly integrate Large Language Models (LLMs), traditional WAFs and static analysis tools fail to catch probabilistic threats like prompt injection and jailbreaking. This session moves past theory into practical defense for engineers using LLMs. We will dissect the "AI Attack Surface" and demonstrate how to use open-source tools like Garak and PyRIT to automate Red Teaming. Attendees will learn architectural patterns for "Guardrails," methods to prevent "confused deputy" attacks, and techniques to verify model supply chain integrity. Leave with a blueprint for securing your AI workloads today.

See Presentation