Data Scientist 2

Gap Inc. • San Francisco, CA

4d • $206,565 - $216,565 • Remote

About The Position

Designs, develops, and maintains production-scale distributed machine learning pipelines using PySpark, Databricks, Delta Lake, MLflow, and Unity Catalog to support e-commerce recommendation systems across multiple brands and markets. Implements advanced machine learning and deep learning models, including neural collaborative filtering and transformer-based sequential recommendation systems, and integrates them into end-to-end production workflows. Owns complete machine learning workflows, including data ingestion, feature engineering, model training, inference, versioning, and automated refresh processes, operating with minimal technical supervision.

Develops advanced feature engineering frameworks combining multi-modal product attributes, customer behavioral signals, and temporal weighting logic to enable large-scale personalization. Collaborates directly with Product Managers and cross-functional partners to translate business requirements into technical system designs, define success metrics, and document implementation constraints. Builds and maintains CI/CD workflows and deployment automation using GitHub Actions and Databricks workflows to support testing, validation, and production releases of machine learning systems.

Designs and implements data governance, validation, and monitoring mechanisms to ensure data quality, lineage, reliability, and compliance of production ML assets. Optimizes distributed processing performance and cloud resource utilization to balance model accuracy, processing latency, and infrastructure cost constraints. Telecommuting is permissible from any location in the US.

Requirements

• Master’s degree in Data Science, Computer Science, Computer Information Systems, or a related field.
• Four years of work experience in the job offered or a related role.
• Experience with transformer-based deep learning architectures, embedding-based modeling, recommendation and personalization systems, collaborative filtering, content-based filtering, matrix factorization, re-ranking, production-scale machine learning systems, MLOps, model lifecycle management, and ML pipeline automation.
• Experience with Azure Databricks, Apache Spark (PySpark), Delta Lake, and distributed data processing.
• Experience with CI/CD using GitHub Actions.
• Experience with cloud-based machine learning platforms, eCommerce analytics, clickstream data analysis, customer behavior analytics, and large-scale data integration and cleansing.
• Knowledge of A/B testing methodologies, KPI analysis, advanced feature engineering, supervised learning, and unsupervised learning.
• Proficiency in Python, SQL, production-grade code development, and cross-functional collaboration.

Responsibilities

• Design, develop, and maintain production-scale distributed machine learning pipelines for e-commerce recommendation systems across multiple brands and markets.
• Implement advanced machine learning and deep learning models, including neural collaborative filtering and transformer-based sequential recommendation systems, and integrate them into end-to-end production workflows.
• Manage machine learning workflows covering data ingestion, feature engineering, model training, inference, versioning, and automated refresh processes.
• Develop feature engineering frameworks combining multi-modal product attributes, customer behavioral signals, and temporal weighting logic.
• Collaborate with Product Managers and cross-functional partners to translate business requirements into technical designs, define success metrics, and document implementation constraints.
• Build and maintain CI/CD workflows and deployment automation using GitHub Actions and Databricks workflows.
• Design and implement data governance, validation, and monitoring mechanisms for data quality, lineage, reliability, and compliance of production ML assets.
• Optimize distributed processing performance and cloud resource utilization while balancing model accuracy, processing latency, and infrastructure cost.

What This Job Offers

• Job Type: Full-time
• Career Level: Mid Level