Kenneth Huang Email & Phone Number

Los Angeles, California, US

• Optimized the lambda/sqs inference pipeline to reduce both costs and latency for recommender predictions by over 90%
• Developed an automated credentialing process using OCR, NLP, and web scraping to verify documents in under 10 seconds
• Reduced the false rejection rate of the credential verification pipeline by 33%~ and improved f1 score by 35%~, saving 90+ hours per month in the professional onboarding process

Los Angeles, California, US

• Conceptualized, developed, and deployed company's first ML-driven ranking/recommender system (XGBoost model) within 9 months, leveraging AWS for preprocessing and inference, H2O.ai for training, and CometML for.
• Drove a 50%+ increase in mobile app shift impressions within the first month of recommender's launch
• Led end-to-end development of: - Airflow & Glue pipelines, for building viable classification training datasets (TB sized) to RDS - SageMaker & CometML training pipelines, for fast experimentation, reporting, and.

Menlo Park, CA, US

• Analyzed accuracy of internal data labeling efforts using Bento and Jupyter dashboards
• Designed and validated OCR templates to ensure accurate invoice parsing, driving automated spend classification at scale

San Jose, California, US

• Revamped excel workflows using Python to automate quarterly forecasting analysis, reducing manual labor by over 50 hours per month

Santa Barbara, CA, US

• Designed lower-division, scientific computing labs with a team of undergraduate physicists
• Implemented a python toolkit for experiments involving I2C sensors, Raspberry Pi, and Lagrangian mechanics

Tampa, Florida, US

• R&D an Android app for facial recognition with the objective of deploying program to clients in populous war zone areas