Software Engineer Engineering / Machine Learning Engineering

Sung-Ying (Steven) Yang

858-***-**** *******.****@****.*** github.com/SungYinYang

SKILLS

Programming Languages: Java, Python, SQL, R, Matlab, C, JavaScript, HTML, CSS, JSON, PHP Frameworks: Pytorch, Tensorflow, Sklearn, pandas, React JS, Django, Hadoop Databases: MySQL, MongoDB

Platforms/Softwares: AWS(EC2/VPC/ELB), Apache Tomcat, Eclipse Java EE, Firebase, Docker, Postman, Git Strengths: Bayesian Inference, Clustering, Regression, Predictive Modeling, A/B testing, Machine Learning Algorithms (KNN, SVM, K- means), Database Architecture, Survival Analysis, Trend Analysis, Time Series Analysis, Deep Learning (NLP, CNN, TensorFlow) Data Visualization: Tableau, D3js, Python (seaborn, matplotlib), Elasticsearch and Kibana EDUCATION

San Jose State University San Jose, CA

M.S. in Software Engineering - Data Science Specialization August 2019-May 2021 University of California, San Diego La Jolla, CA

B.S. in Mathematics and Computer Science Major August 2015-June 2019 WORK EXPERIENCE

Machine Learning Engineering Intern June 2017–August 2017 Foxconn Technology Group Houston, TX

• Worked with a mentor and broader teams across the company to advance software machine learning capabilities, wrote production quality codes and improved the performance and robustness of new AI technology

• Assisted in building the next generation of machine learning systems by designing novel algorithms to solve industrial-AI problems, applied expert software development skills to ML-related coding projects

• Deployed Hadoop Cluster to collect and store business data from production line, defined appropriate data reports and dashboards from Microstrategy APIs to inform solutions creatively and support the decision-making process

• Enabled a Single Sign-on Function using LDAP, improved serialization and deserialization efficiency by 20% using Microstrategy Business Intelligence platform

• Consolidated documentation and related materials to help internal users build on top of contributions, influenced engineering teams through presentation of data-based recommendations, communicating state of business, experiment results, and spreading best practices

PROJECTS

AV Automation Testing

• Established a 3D time-based model and provided test automation solutions for Autonomous Vehicle

• Tested Baidu Apolo automatically using LGSVL simulator based on user requirements

• Built the output result board using Python Flask and deployed it to Amazon Web Service EC2

• Created Total 12 pre-crash scenario templates based on pre-crash scenarios from NHTSA paper Street Detection from Lane Segmentation

• Developed an application to automatically detect streets from dashcam videos by Lane Segmentation

• Referred to the method of IEEE 2016 paper and enhanced the results from old method, trained the model on the Kitti dataset

• Built FCN 8, FCN16, and FCN32 in Google Colab GPU using VGG 16 classifier (TensorFlow) Job Recommendation System (Data set: https://www.kaggle.com/c/job-recommendation/overview)

• Developed and compared two different recommendations systems: Content-based filtering and Collaborative filtering

• For content-based recommendation: Extracted keywords from job descriptions and job resume by using NLTK

• For Collaborative filtering recommendation: Extracted keywords by TF-IDF from each job description Credit Card Fraud Detection (Data set: https://www.kaggle.com/mlg-ulb/creditcardfraud)

• Visualized Credit Card Fraud dataset from Matplotlib and Seaborn

• Preprocessed the data including removing outliers and resampling the dataset using Sklearn

• Trained and compared different supervised learning classifiers such as SVM, Naive Bayes, KNN, and Logistic Regression and tuned proper hyper-parameter by cross-validation.

Contact this candidate