I’m an AI Safety & Red Teaming practitioner with a multidisciplinary foundation shaped by a Bachelor of Arts in Arts & Technology and an Associate of Computer Science. That mix of creative design, technical problem-solving, and hands-on experimentation lets me approach LLM failure modes from multiple angles: visual, behavioral, and analytical. I build adversarial sandboxes, prompt-injection tests, and multimodal stress-testing environments that reveal how models break and how their safety systems can be strengthened.