Data Engineer
diconium data GmbH
مجموع سنوات الخبرة :3 years, 3 أشهر
Designed and implemented data pipelines in Azure to handle real-time vehicle data. Also utilised Bicep for infrastructure deployment, ensuring consistent and automated deployment processes. Implemented and optimized Azure services for monitoring and alerting, contributing to system robustness. Designed and implemented a circuit breaker architecture to proactively handle and stop services in case of failures, improving system reliability.
Worked closely with stakeholders across departments to design and develop ETL pipelines from external data sources like RSS Feeds, Twitter, Bundestag API, etc. Designed and developed scalable databases capable of ETL process using PostgreSQL Developed data enrichment pipelines using the wiki-data knowledge base Developed event-driven architectures using NATS as a Publish/Subscribe messaging service. Increased the speed of the pipelines by 200%, by utilizing multiprocessing and better query mechanics.
Analyzed data to find associations among the variables and developed machine learning models with an accuracy score above 95%. Converted data into actionable insights by predicting and modeling future outcomes Languages and Libraries: Python, R, ggplot2, Numpy, Scikit-learn, Seaborn, Matplotlib, dplyr etc. Algorithms: Regression, SVM, Random Forests, XGBoost.
Worked on building efficient classifiers to predict labels using the SVM, XGBoost, and Logistic Regression with reduced training time. Developed Interactive plots using Plotly and Seaborn Languages and Libraries: Python, Pandas, Numpy, Scikit-Learn, Matplotlib, Seaborn, Plotly, etc
Master's Thesis Topic: Sentiment Analysis on Twitter data for trend prediction in agriculture stock market
Graduated in Top 5% of Class. Elected as Technical Coordinator for Annual Sports Fest SHAURYOTSAVA in 2018
لقد تم حذف الرابط بسبب انتهاكه لسياسة الموقع. يرجى التواصل مع قسم الدعم لمزيد من المعلومات.