David Liu

Lead data scientist on Shipt's Personalization team; recommender systems behind every personalized shelf on the platform. Mentored 4 data scientists including 2 direct reports.

• Delivered up to 23% Personalized GMV lift across A/B-tested shelves (Trending Items, Similar Items, Deals For You, Complementary Items) over 90 days.
• Designed and built a two-tower deep-retrieval model replacing the legacy ALS recommender; 3–15% lift on Deals shelves and 11% higher CTR; offline +406% NDCG, +87% novelty, +19% long-tail coverage vs. baseline.
• Designed user/product embeddings going beyond text matching (descriptions, categories, pricing, retailer info, dietary preferences, behavioral signals); FAISS ANN infrastructure on GCS for low-latency retrieval at scale.
• Created the Personalization Interaction Score — a composite funnel metric (views → clicks → ATC → purchases, weighted by depth) that replaced single-metric optimization. Adopted by teammates for next-gen real-time recommenders.
• Developed a price-weighted ATC approach for coldstart users; 47% engagement lift and 8% more first-time orders over 90 days; technique adopted across other shelves.
• Built an automated Shelf Attribution pipeline using fuzzy-string matching; identified previously reported 5% attribution figures were irreproducible (actual: 1–4%); transparent reporting catalyzed a shift to defensible success metrics.
• Designed and built a Customer Intelligence Platform (CIP) and an "Essentials" recommender shelf usable as both a standalone shelf and a relevance filter for others.
• Partnered with Engineering to replace brittle CSV-based recommendation delivery with Kafka-based pipelines across all legacy recommenders.
• Designed a Retrieval-Augmented Generation system over Shipt's internal retailer catalogs and built the business case that secured agentic-AI investment.
• Served as the team's sole data scientist for its first four months — maintained 16 Discovery Science repos while designing next-generation infrastructure.

Core ML engineer at a genomics company developing a blood test for early-stage cancer detection. Worked at the intersection of infrastructure and research.

• Key contributor to Freenome's core multiomics cancer-detection model that predicts cancer stage (1–4) from blood-draw data; built data abstractions for petabyte-scale genomic datasets that unblocked cross-analyte feature development and accelerated training/evaluation cycles.
• Built a model-comparison system tracking research-vs-production model performance side-by-side — required for FDA audit compliance, gave the team confidence that production models stayed aligned with research intent.
• Designed and built large portions of Freenome's distributed ML training and serving platform used daily by 30+ scientists; scaled CPU-bound training across O(100) machines, supported leave-one-out / K-fold evaluation, and built reproducible model-artifact storage.
• Led adoption of PyTorch, MLFlow, and RayTune across the ML team — replaced legacy tooling to unlock GPU acceleration, experiment tracking, and hyperparameter tuning at scale.
• Built a cloud-cost monitoring system surfacing the biggest GCP storage and compute expenses; visibility alone drove optimizations saving the company over $10M annually — one of the highest-ROI projects I've worked on.
• Recognized with a Servant Leadership Award, elected by managers and peers across the engineering organization.

ML systems for health-insurance claims processing — accuracy translates directly into operational cost savings.

• Designed a ranking model matching human workers to claims tasks based on skill, history, and complexity; $7M annual value by reducing manual task assignment and the need for additional hires.
• Built a classification model partitioning sensitive patient documents (image + text) to route claims to the correct processing workflow.
• Developed internal AWS tooling and production API infrastructure for the ML team's deployment pipeline.
• Led a cross-functional tiger team prototyping a conversational chatbot (Rasa + HuggingFace NLP) for internal claims-inquiry workflows.

ML models for an executive-recruiting firm; full pipeline from data collection to model serving.

• Developed a model suite: a job-departure-likelihood classifier, a regression model predicting team sizes from resume features, and a candidate-ranking model using a custom NDCG listwise loss.
• Built an end-to-end framework for rapid model prototyping, training, evaluation, and serving — enabled the team to iterate on new models without re-engineering infrastructure each time.
• Wrote scrapers harvesting structured candidate data from public sites and APIs.

• California Institute for Energy and Environment (CIEE) — built a recurrent neural network for predicting building energy usage, exploring how temporal consumption patterns can inform smarter grid management.
• Bengson Research Lab, Sonoma State — applied ML to EEG data to predict individualized occipital lobe activation patterns; demonstrated early feasibility for brain-computer interface applications.

• Data Science Intern, Castlight Health (2017) — entity matching and deduplication pipeline using gradient-boosted classifiers with hard-negative mining; 85–95% precision/recall across hospital, facility, and practitioner entities.
• Data Science Contractor, Riviera Partners (2016) — team-size prediction model from public data; Python wrapper for survival-model time-series analysis; Flask model-serving infrastructure.
• URAP, Berkeley Institute of Data Science (2016) — mapped UC Berkeley course progression across majors via class-taxonomy organization and deduplication.
• Data Science Intern, Doximity (2015) — gradient-boosted classifier for malformed scraped articles; reverse geocoding + fuzzy string matching to link doctors in news articles to facility profiles.