Mario

about

I'm a Computer Science graduate and AI data trainer with hands-on experience in data annotation, reinforcement learning from human feedback (RLHF), and large language model evaluation. At Telus International, I evaluate and help improve models including Gemini and ChatGPT, focusing on factual accuracy, reasoning, and adherence to complex instructions. I create challenging prompt-response pairs and assess human preferences to support model quality and alignment. I also bring experience in web application quality assurance, functional testing, vulnerability analysis, and bug documentation. I can review application behavior, communicate issues clearly to engineering teams, and produce technical documentation and security recommendations. My ongoing nursing studies add a healthcare perspective to my AI evaluation work, including reviews of medical reasoning, anatomical terminology, and patient-safety-sensitive content. I'm detail-oriented, analytical, and comfortable managing tasks independently while collaborating asynchronously with remote teams.