I am an artificial intelligence specialist focused on Responsible AI, governance-aware system design, and human-centered developer experience. This portfolio documents my applied AI safety work on evaluation, oversight, and human-in-the-loop systems, with a focus on how AI behaves in real-world institutional settings.
I design tools and frameworks that help organizations deploy AI responsibly by making risk, intent, and impact visible early in the lifecycle. My approach emphasizes human oversight, proportional governance, and clear decision documentation, ensuring AI systems remain accountable, interpretable, and aligned with real-world constraints.
Alongside governance systems, I study how tone, timing, and interaction design shape user trust in AI. I am particularly interested in how subtle design choices influence perceived agency, reliability, and safety, especially in high-impact or regulated environments.
My work is guided by a balance between structure and human experience.
Strong AI systems are not only accurate or efficient. They are:
I focus on building systems where emotional UX supports—not replaces—control, accountability, and explainability. This means designing interactions that feel calm, intentional, and respectful of human decision-making, rather than persuasive or opaque.
To help shape the responsible emotional layer of artificial intelligence: systems that communicate clearly, respect human agency, and operate within well-defined ethical and governance boundaries.
I believe the next generation of AI systems will be judged not just by what they can do, but by how safely, gracefully, and accountably they interact with people and institutions.
*Explore my featured projects below!