CakeResume Talent Search

reached the Databricks Delta Lake. Established robust guardrails using the combined might of AWS Lambda, Apache Airflow and Databricks, ensuring that data stored in the DataBricks Delta Lake consistently met the highest quality benchmarks. MLOps / Machine Learning / Data Science Utilized Databricks to build a LightGCN-based recommendation system, fine-tuning for precise content delivery. Monitored model versions with MLflow, ensuring continuous integration. Seamlessly merged our recommendation system with Databricks Delta Lake, maintaining a high-quality data influx and elevating system performance. Developed a comprehensive MLOps service on Databricks, spanning from preprocessing to deployment

Agency Lab - PII Data Detection: Develop automated techniques to detect and remove PII from educational data. 2024/04/24 - Silver medal (solo): (Kaggle) U.S. Patent Phrase to Phrase Matching: Help Identify Similar Phrases in U.S. Patents, 2022/06/21 Recommendation system (推薦系統): - Silver medal (solo): (Kaggle) OTTO – Multi-Objective Recommender System: Build a recommender system based on real-world e-commerce sessions, 2023/02/08 - Bronze medal (solo): (Kaggle) H&M Personalized Fashion Recommendations: Provide product recommendations based on previous purchases, 2022/05

Jun– FebThe biggest social media app in Taiwan. ( App store ) This position works closely with the infrastructure team members, data scientists, and product managers. Dcard is the most popular social media app in Taiwan. Support data-team built data pipeline and data center for our home page recommendation system. Implemented dictionary compression utility for a high writing-load database with a 95% compression rate and 60% insert speed improvement. Improved Elasticsearch performance and conducted new query implementation. Rewrote index mapping; as a result, the new index was reduced by 40%, allowing us to build

the CI/CD workflow and generic helm template to support over 30 projects and ensure easy integration with our GitOps deployment. MayMay 2022 Senior software engineer E.SUN Financial Holding Co., Ltd MLaaS platform Introduces MLaaS platform framework based on Kubernetes, consulting on several ML service system designs and operation tasks Kubernetes/golang/Prometheus/minio/airflow/EFK/kafka/argocd/argo-rollout Deploy On-Premise Kubernetes cluster and operation tasks like monitoring, scaling up/down nodes, troubleshooting, and root cause analysis Designed and built ML platform core features

security principles IPv4/v6 networking, routers, firewalls, packet analysis, libpcap, socket programming Monitoring and logging solutions Prometheus, Elasticsearch/Logstash/Kibana (ELK), Splunk, Dynatrace Infrastructure as Code (IaC) tooling Terraform, CloudFormation, Ansible Cloud Infrastructure Amazon AWS, Google GCP, Microsoft Azure, OpenStack Containers Docker, Kubernetes, LXC, openvz Version control systems Git, Subversion, Mercurial, CVS, RCS Praise and Recommendations Along with his impressive technical skill set, Pat has been great to work with. He is a positive, upbeat personality that complements any team he is a part of. I believe Pat is a true example of the type

making for business but also provide tech solutions to our services and products. My contributions includes: Architecture and methodology review for data solutions and various data analytic tasks Translate abstract business problems into solvable engineering components Project planning and management Goal alignment Advanced Algorithm Engineer, OctAug 2020 Data streaming system development for near real time user tagging (JanJulA kubernetes based application aims to link our content delivery system to the online readers according to their real time behaviors. I lead the system architecture design Handle concurrent traffic from over 5M users everyday Leverage google cloud services such as

WEN YU TING (Wendy Wen) Data Analyst、Data Engineer、Data Scientist Taipei，TW [email protected] Core qualifications is using Python, R and SQL server for analysis, and also use distributed computingPyspark for data processing. Find insights from the data and make recommendations and improvements, use BI tool to present data visualization. Also familiar with BigQuery, Amazon and Google Analytics system. Use ML tools to observe therelated variables from the data, design variables, model, and analyze the prediction results. Tool Skill Python、R、Pyspark、SQL server、Jupyter、BigQuery、AWS、Google Analytics、Data Studio Professional