Prismberry Technologies

Role – Senior Data Scientist

 Defining Cloud and DevOps roadmap to manage service for IOT data ingestion of about 300+GB with 99.5 % uptime

 Reduction in Infrastructure cost and virtual machine footprint by 34% after implementing microservices and improved latency and throughput using auto scale ingestion

 Maintaining Log monitoring, load testing, alerting and playback system of data ingestion

 Resolved operational issues concerning Dataops infrastructure - databases, data pipelines, data warehouses and storage

 Leading team on data science and engineering application building ETL and ML automation platform that drives business

 Built prediction model for identifying SKUs at risk, for cross-sell and up-sell in retail store leading to annual benefit

 Hands-on experience from scratch to build machine learning model and deriving business insights using tableau dashboard, A/B test requirements and metrics

Skills Learned

Data Science

Python, Pandas, PySpark, Selenium, Scikit, Keras, A/B Testing, Regression, Time series analysis, Clustering, Linear Mixture Model

Databases

Cassandra, Kairos DB, Azure SQL, Big Query

Data Engineering

Kafka, Jenkins, IOT Hub, Locust, Docker, Image Registry, Kubernetes, Airflow, Geoserver

Visulaisation

Tableau, Kepler.gl