Yi Wang

Pittsburgh, PA ***** +1-404-***-**** adu2u6@r.postjobfree.com https://github.com/YiWang0516 EDUCATION

Carnegie Mellon University Pittsburgh, PA

MS in Music and Technology - Machine Learning and Software Development Focus Aug 2021 - May 2023 Emory University Atlanta, GA

BS in Computer Science, and Double Major in Music Aug 2017 - May 2021 Honors: Dean’s List of Emory College of Arts and Sciences for Fall 2018 semester Course Highlights: Deep Learning, Machine Learning, Cloud Computing, Multimodal Learning SKILLS

Technical Skills: Java, Python, C/C++, SQL, Spark, Spring, Kubernetes, Angular.js, Azure, AWS, Terraform Industrial Skills: Design Patterns, Service Oriented Architecture, Source Control, Agile Development Languages: English (fluent); Japanese (fluent); Chinese (native) PROJECTS

Twitter User Data ETL Microservice Nov 2022

● Implemented Spark ETL on Twitter user data with Azure Databricks and HDInsight and designed schema for fast query of user interaction score data

● Implemented interaction score algorithm as Spring microservice and deployed with Kubernetes configuration using AWS EBS as persistent volumes for Mysql service achieved over 10k RPS with 0.8$/h cluster Social Network Website Backend Oct 2022

● Deployed message and time series data storage pipeline with HBase, social graph data storage pipeline with Neo4j, user info with MongoDB capable of accessing user timeline in less than 200 milliseconds QR Code Microservice Oct 2022

● Implemented and deployed QR encoder and decoder algorithm as Jooby microservice on Kubernetes cluster and achieved over 100k RPS with 0.8$/h cluster and AWS elastic load balancer Noisy Label Detection for Speaker Recognition Apr 2022

● Submitted paper to IEEE ICASSP on research in performance of various commonly used ASV(Automatic Speaker Verification) loss functions under different noise settings Video Content Classification Feb 2022

● Trained video content classification model with CNN video features and PaNN audio features and achieved test accuracy of 71.3% and implemented Django web server with RESTful API on model inference request Uber Matching System Nov 2022

● Implemented Kafka producer with Uber data and Samza consumer to analyze and match rider requests with driver locations, rider health status with local restaurant advertisement. Cab Fare Prediction App with Google AI Platform Training Apr 2022

● Trained NYC cab fare prediction model using XGBoost with Google Hypertune and deployed as Flask app on Google App Engine. Integrated other GCP APIs including speech-to-text, NER, Map with model API into a voice input cab fare prediction web service.

EXPERIENCE

Software Architect Intern Atlanta, GA

Federal Home Loan Bank Jun 2020 - Aug 2020

● Improved database access speed by 20% with denormalization and indexing

● Integrated new security key service into enterprise database system verification program

● Implemented backend database read and write microservice for internal information dashboard Software Development Intern Suzhou, China

Suzhou Fangxing Information Technology Jun 2019 - Aug 2019

● Integrated Tesseract OCR Engine for engineering drawing text extraction and localization

● Developed interactive 3D view for online model design platform with THREE.js NLP Software Developer Atlanta, GA

Emory University Nov 2019 - Dec 2020

● Contributed to Open Source Emory NLP project: github.com/NLP-Suite/NLP-Suite/wiki/The-NLP-Suite-Team

● Assisted Professor Roberto Franzosi and his team in data processing of several published Sociology papers

Contact this candidate