Data Scientist at CrowdStrike
Cristian Popa
Data Scientist
ML Engineer
Docker
Jira
Python
PyTorch
scikit-learn
After many years at CrowdStrike, I was faced with many problems to solve in the best way I could. This included, but obviously is not limited to:
Tabular tasks - classification, regression, embedding
Deep learning - primarily focused on NLP, but also multimodal classification and embedding
Big Data - large data flows that required parallel processing; used Spark
Model delivery - Docker and Airflow were the main technologies used here