AI inference systems
Compute systems are optimized for executing trained models efficiently at scale.
What It Is
Data Science is the interdisciplinary field of extracting knowledge and insights from data. On this site, it matters because it transfers across technical, operational, and venture work instead of staying trapped in one narrow context.
Learn more: https://en.wikipedia.org/wiki/Data_science
Machine learning systems
Pipelines train models on data to produce predictive or generative outputs and improve performance through iteration.
Feature engineering systems
Processes transform raw data into structured inputs that are better suited for learning and inference.
Machine Learning Pipeline for Automated Ad Pricing
Before TensorFlow existed, built a continuously-learning SQL-based machine learning system that optimized real-time bid pricing for programmatic advertising —...
Model serving systems
Infrastructure deploys trained models for real-time or batch inference under latency and scaling constraints.
Demographic Prediction Model and Machine Learning Pipeline
Built predictive audience demographic datasets using graph databases and AI/ML. Trained models to predict demographic attributes of mobile device audiences...
Enhanced IP Geolocation Model for Security and Verification
Designed a novel IP geolocation confidence model combining location observation data with network topography analysis to improve the accuracy of geographic...
Geospatial Systems
Systems model physical space using coordinates, polygons, and clustering to derive insights and build products from location data.
GIS / geospatial systems
Spatial systems represent and analyze location-aware data so geographic relationships can be integrated into products and decisions.
Location Observation Fraud Outlier Identification
Used Tableau and sampled data to identify impossible or improbable movement patterns in location observation datasets, then designed a system to tag and filter...