- Build and scale a data pipeline handling massive data volumes exceeding a million predictions per second.
- Design and execute experiments across feature engineering, model optimization, and evaluation of new ML tooling.
- Apply classical machine learning on tabular data and develop NLP and embedding solutions for user profiling.
- Contribute to deep learning initiatives integrating feature embeddings with text-based analysis.
- Collaborate with engineering teams to refine and optimize data processing pipelines.
- Integrate AutoML techniques into existing workflows to automate analysis.
- Explore new data preprocessing methods and build visualizations to monitor experimental performance.
AWSDockerPython+5 more