My work sits at the intersection of AI engineering, data infrastructure, and real-world domain problems-exactly the kind of interdisciplinary bridge VALIANT is built to strengthen. I’ve built and shipped AI-facing systems that make model behavior measurable and reliable (e.g., Promptly, an LLM engineering platform with a quantitative evaluation engine and A/B testing dashboard), and I’ve applied machine learning pipelines to complex scientific and infrastructure settings (e.g., transfer-learning-friendly simulation tooling for chemical kinetics, multivariate analysis for water treatment optimization, and sensor/anomaly detection work for smart water systems). Across these projects, I focus on turning AI from “demo” into “decision-grade” technology: rigorous evaluation, reproducible pipelines, and deployment-minded collaboration with stakeholders and domain experts. In VALIANT, I hope to contribute this evaluation-and-translation skillset, building AI systems that are not only technically strong, but also interoperable with domain workflows and accelerated through cross-disciplined research.