Personal details

Hang P. - Remote

Hang P.

Timezone: Eastern Time (US & Canada) (UTC-4)

Summary

Passionate developer who is good at designing and implementing end-to-end data solution including data ingestion, transformation and machine learning prediction to provide business insights for clients.

Work Experience

Machine Leanring Engineer
Royal Bank of Canada | Jan 2019 - Present
Python
Java
Pandas
Machine Learning
Apache Spark
Deep Learning
H2O
Chatbot
- Work with stakeholders throughout the organization to identify opportunities for leveraging company data to drive business solutions. - Mine and analyze data from company databases to drive optimization and improvement of product development, marketing techniques and business strategies. - Assess the effectiveness and accuracy of new data sources and data gathering techniques. - Develop custom data models and algorithms to apply to data sets. - Use predictive modeling to increase and optimize customer experiences, revenue generation, ad targeting and other business outcomes. - Develop A/B testing framework and test model quality. - Coordinate with different functional teams to implement models and monitor outcomes. - Develop processes and tools to monitor and analyze model performance and data accuracy.
Data Engineer
Scotiabank | Aug 2018 - Jan 2019
Java
Continuous Integration
Google Cloud Platform
Continuous Deployment
Apache Kafka
Microservices
Google Dataflow
- Designed and built dataflow pipeline to ingest high volume data from enterprise data lake to public cloud with PII fields encrypted and tokenized. - Developed and optimized both streaming and batch data processing pipeline using Apache Beam and Google Cloud Platform. - Designed and implemented pipeline regression test framework and deploy script for Continuous Development and Continuous Delivery (CI/CD). - Worked on proof of concept to design event driven microservices backboned by Kafka as event bus using domain driven design concept. - Systematically document designs and solutions on confluence pages and periodically showcase end product to product owner.