About

Evaluation Science & Insights Lead specializing in the development and launch of AI-driven experiences at scale—focused on Search, Personalization, and Generative AI. At Apple, I lead evaluation strategy for Apple Podcasts within the Human-Centered AI team in Services Engineering, shaping how we test and deliver innovative ML-powered experiences used by billions of people around the world.

My work centers on integrating human insight into every stage of the machine learning lifecycle. From prompt evaluation and search relevance to recommendation tuning and Generative AI output ranking, I design scalable evaluation frameworks that ensure our intelligent systems are intuitive, trustworthy, and aligned with real-world user needs.

Beyond measuring quality, I help bring to life first-of-their-kind AI-driven experiences—grounded in user research, validated through rigorous offline testing, and aligned with Apple’s core principles of privacy, accessibility, and exceptional user experience.
Previously at Scale AI, I worked on large-scale data operations supporting Natural Language Processing (NLP) model performance, annotation quality, and scalable infrastructure—strengthening my foundation in applied AI and high-integrity ML development. My background spans product strategy, experimentation, UX research, and human-centered design, supported by academic experiences at Stanford, UC Berkeley, and Saint Mary’s College of California.

What drives me is building technology that empowers creators, enhances discovery, and reflects the needs of the people it serves.

Outside of my core work, I’m passionate about the ethical and social dimensions of AI. I actively support opportunities to mentor, guest lecture, or collaborate with nonprofits and mission-driven organizations focused on responsible AI, tech accessibility, and inclusive innovation.

If you're working at the intersection of people, products, and emerging technology—or envisioning what meaningful, responsible AI can look like at scale—I’d love to connect.