Voice Ingestion Pipeline: Ingest real-time voice data from a specific target source, process it, and safely convert/integrate it into the Capital One data ecosystem.
Model Feature Engineering: Collaborate directly with Data Scientists running biometrics models to build out new feature sets that continuously improve model performance and accuracy.
Platform Stability & Automation: Partner with the backup operations team to maintain system stability, while proactively looking for architecture opportunities to automate the ingestion and transformation processes.

Must-Haves: High proficiency in Python, AWS, Snowflake, and AWS Glue.
Strong Plus: PySpark / Apache Spark for distributed data processing, Complex data modeling (most core data models and pipelines are already built and established).
Soft Skills: Highly independent working style, proactive problem solver, and strong communication skills to sit between engineers, backup operators, and data scientists.

Python Developer-W2

Related