About

Divyank Garg is a highly skilled Software Engineer-3 (Senior Data Scientist) with over 5 years of experience in the semiconductor industry. He has expertise in data science, business analysis, data analysis, and data pipeline management, using machine learning and AI concepts. Divyank is proficient in various programming languages such as SQL, R-studio, Python, and has experience working with tools like Kafka, Docker, Ray, Tableau, and other ML tools. Divyank holds a Master's degree in Industrial Engineering with a focus on data science and data analytics from Texas A&M University. He has worked with Juniper Networks for the past five years, where he has developed automatic prediction models for detecting RMA by analyzing system logs with the help of ELK stack in AWS. He has also created multistep LSTM and Neural Prophet models to forecast the bps value of the network for the next day, with an impressive MAPE of 15%. Additionally, Divyank has built multivariate LSTM Auto-encoder models to detect anomalies by calculating the reconstruction error for 100 network streams independently. During his tenure at Juniper Networks, Divyank has also worked on building parallel distributed clusters using Ray Python in Juniper's internal cloud, which resulted in a 90%, 50%, and 92% time improvement in Sklearn model selection, SVC model, and Grid search hyperparameter tuning algorithms, respectively. He has also developed a reusable live stream data-pipeline POC using Kafka in Docker to enable run-time on-demand provisioning of data pipelines to address different ML application use cases for Juniper telemetry data. Divyank has a strong background in data analysis and has worked on various projects such as forecasting total amount spent for the next quarter, making Tableau dashboards to report labor allocation and quarterly amount spent for projects, and extracting data from server MySQL RDBMS using Python and merging it with engineering data from smartsheet using API calls. He has also created ER diagrams and Relational schema to learn the relationship between tables and executed SQL queries to get desired tables. Overall, Divyank has a relevant experience of 5.03 years and is skilled in various technologies such as Data Science, Research Scientist, Software Engineer, Python, SQL, ML, NLP, Kafka, AWS, AI, Deep Learning, Docker, Random Forest, Spark, Text Classification, Hyperparameter, Scikit, MySQL, Integration, Sentiment Analysis, Search, Flask, J