hengtao tantai
Architect , AI Researcher
About
I've been in the industry for 18 years because my job coincides with my hobby and I really love my work. I have extensive experience in big data, data science and backend development.
Work Experience
Self-employed
2022 – Present
Consultant
Provide big data consulting consultant for company
Highlights
- China Everbright Bank bigdata platform architecture upgrade CDH-> CDP
- Data platform construction of a catering group company in Beijing
Fuwai Hospital
2019 – 2022
Data Scientist
Data platform and AI-related work in IT department
Highlights
- Data warehouse architecture and ETL process refactoring,Update Data warehouse architecture from oracle to hadoop ecosystem
- Data management platform for data exchange with third-party systems
- MRI image ventricular segmentation
DECDT
2017 – 2019
Data Architect
Highlights
- in-video ads monitoring system
- real-time monitoring system for celebrity commercial value tracking, public opinion , endorsement performance monitoring
LeEco
2014 – 2017
Data Architect
Highlights
- Optimized the big data architecture,reconstructed datawarehouse and ETL workflow
- Collect and process user behavior data and support advertising recommendation system
Alibaba / Aliexpress
2011 – 2013
Bigdata Expert
Highlights
- Build a tracking system using hadoop , hive, and spark. create data warehouses and etl processes using sql
- collect keywords from competitors' websites and Improved relevance of search keyword drop-down boxes through machine learning
- Online Marketing data analysis
Rising antivirus software
2007 – 2011
Web Developer
Highlights
- Malicious Index Service,create indexes for virus libraries and antivirus guidance documents
- Malicious Websites Classification,skearn has not been released at that time , so use python implement kmean and logistic regression algorithms
- develop website ikaka.com with java python and jquery
Projects
- Overfit: Machine learning blogs and communities,Published articles related to machine learning and deep learning, over 100,000+ followers
- Deepfeed: Deep Learning Blog/Article Aggregation
- Pytorch Handbook: open source book aimed at getting those who want to use PyTorch for deep learning development and research started quickly. The Pytorch Handbook includes all the PyTorch tutorials that have been tested successfully
Education
-
2000 2004
Beijing Union University
Bachelor
Computer Science
Skills
Backend
Expert
Python
Django
SQL
NodeJS
Shell
Redis
Prometheus
BigData
Expert
Hadoop
Hive
Hbase
Spark
Flink
Presto
Kafka
CDH/CDP
Doris
Data Warehouse
Data Engineer
Data Science
Expert
Machine Learning
Deep Learning
Pandas
Numpy
Sklearn
Pytorch
Frontend
Beginner
Javascript
HTML
CSS
Bootstrap
React
Publications
Parctice of Data Quality Management in Health Industry