# Ding D. > SDE @ Expedia Group Location: San Francisco, California, United States Profile: https://flows.cv/dingd HELLO, WORLD. I’m passionate about developing AI-driven applications and designing scalable backend services. My focus is on ensuring seamless integration and robust performance with GenAI, delivering enterprise solutions that drive innovation and enhance user experiences. ## Work Experience ### Software Development Engineer @ Expedia Group Jan 2020 – Present Launched and delivered AI-powered travel products across mobile and web platforms. Agentic AI • Property QnA AI Agent Intelligent Itineraries Service • Launched LLM-powered personalized itinerary recommendations (flights/lodging/activities); drove retention and conversion via internal and third-party data integration; scaled globally to 3 brands, 7 languages, 27 locales. • Designed backend systems (Kotlin/Spring Boot/MongoDB/Kafka) for scalability and availability. • Enhanced GenAI performance (accuracy/completeness/relevance/consistency) via prompt chaining, fine-tuning, model evaluation and seamless migration; reduced latency and ensured AI safety. • Leveraged MongoDB, asynchronous processing, and Kafka for efficient data flow and scalability. • Developed Spinnaker CI/CD pipelines; implemented Splunk/Datadog monitoring for proactive issue resolution. • Collaborated with cross-functionally (product/ML/design) to align project goals, drive innovation and achieve impactful results. Offline Platform Booking Detection • Productionized a two-stage model workflow (in-house RoBERTa + GenAI) to detect platform policy violations (Python/TorchServe/Docker/K8s/AWS). • Built real-time inference services and model packaging deployed via a robust RESTful architecture. Conversational Trip Planning with ChatGPT • Marked the company’s first adoption of GenAI, enhancing travel planning experience through AI assistants. Real-time Virtual Agent Application • Supported 10+ brands, 15k agents and 100M+ million customer interactions daily (React, Node.js). Task-Oriented Dialogue Model • Fine-tuned casual language models (DialoGPT) using in-house data sources to engage travelers with human-like dialogue. ### Data Science Intern @ Mozilla Jan 2020 – Jan 2020 | San Francisco Bay Area • Defined core business metrics and performed exploratory analysis on terabytes of Firefox user behavior data using SQL (BigQuery, PySpark) to identify growth areas of search monetization. • Built production ETL pipelines for derived datasets used in house daily and contributed to open source repositories. • Predicted ad clicks using predictive models (Logistic Regression, Random Forest, XGBoost) via scikit-learn and identified key features to increase ad revenue. Final model achieved 0.89 AUC and 0.81 accuracy. • Delivered reports using R (Shiny, ggplot) to support multiple business decisions for the management teams. ### Software Engineer Intern @ Siemens PLM Software Jan 2018 – Jan 2018 | Greater Los Angeles Area • Increased purchase and retention rates by implementing a system to track customers through their entire lifetime. • Developed and deployed an end-to-end data analytics and visualization dashboard that provides insights into online sales of company products. • Presented app to company executives and used the Agile software development lifecycle to incorporate their suggestions. ### Game Operations Analyst Intern @ MOONTON GAMES Jan 2017 – Jan 2017 | Shanghai City, China • Partnered with multiple teams to design and establish periodically releases on mobile game features to optimize metrics. Performed data analysis, visualizations, quantitative research, and delivered business recommendations. ## Education ### Master of Science - MS in Data Science University of San Francisco ### Master of Science - MS in Computer Science University of Southern California ### Bachelor of Science - BS in Computer Science and Business Administration University of Southern California ## Contact & Social - LinkedIn: https://linkedin.com/in/dindindin --- Source: https://flows.cv/dingd JSON Resume: https://flows.cv/dingd/resume.json Last updated: 2026-03-29