Senior Data Scientist

Responsible for using machine learning (ML) and analytics to drive Shipt’s business forward. This position requires a Master’s degree or equivalent in Data Science, or Statistics and 4 years of experience deploying ML based solutions for business problems. Must also have 48 months of experience with each of the following:

(1) multi-stage multivariate experiment design using Bayesian optimization, hierarchical A/B testing with dynamic sample rebalancing via Airflow DAGs, and applying synthetic control methods for causal impact analysis in non-randomized settings;

(2) working with TensorFlow, PyTorch, and XGBoost within end-to-end pipelines, deploying models via AWS SageMaker, and fine-tuning hyperparameters using Bayesian search optimization;

(3) designing, developing, and maintaining scalable data pipelines for processing large-scale datasets, including implementation of indexing and optimized file formats including LIBSVM to achieve significant performance improvements;

(4) leading and mentoring data science teams, including directing analytical projects, implementing quality control processes, and fostering the professional development of junior data scientists; and

(5) working with the following data science technologies: Python, SQL, Snowflake, Jupyter, Git, AWS (including SageMaker, EMR, and Elastic Beanstalk), Greenplum, Tableau, PySpark, Pandas, NumPy, SciPy, Matplotlib, ggplot2, Kepler.gl, Flask, Jinja, Adobe Analytics, and Adobe Target.

Will accept experience gained before, during or after Master’s program. Telecommuting available from anywhere in US.