
I’m a passionate AI training specialist with extensive experience in RLHF through my work at Outlier AI, where I’ve contributed to some of the most advanced chatbot alignment and evaluation projects. My work spans prompt and system prompt engineering, safety testing, rubric creation, multimodal input evaluation, and detailed response writing and justification across dozens of categories and intent types. With a strong eye for nuance and consistency in model behavior, I take pride in crafting high-quality, human-aligned interactions. I’m currently earning my B.S. in Computer Science, which further fuels my commitment to building safe, intelligent, and user-centered AI systems.