Tech Stack

Description

You will design and implement durable, efficient software solutions to handle massive volumes of structured and unstructured data for training complex ML models and serving them online. You will build scalable offline and online ML platforms to support ranking, recommendation, and business decision-making, transforming billions of records and petabytes of logs into consumable data objects. This role involves serving complex ML models in real-time to help millions of customers search and discover products.

Requirements

• Bachelor's degree in computer science, electrical engineering, mathematics, statistics or closely related fields
• 8 years of professional experience in applied machine learning
• Experience in machine learning, deep learning, and statistical modeling
• Proficiency in Python and/or Java, with experience in building production grade ML systems

Responsibilities

• Proactively drive the execution of end-to-end data platform and data quality roadmap for Search Discovery ML efforts
• Take ownership, consolidate and optimize the Search Discovery core data logging, processing, and ML model training pipelines
• Develop and scale data infrastructure that powers batch and real-time data processing, monitoring, and debugging for ML experiments
• Drive design and implementation of scalable ML based ranking system and online ML inference services
• Build strong cross-functional partnerships with Data Scientists, Analysts, Product Managers, Indexing Platform Engineers, Ranking Engineers and Data Platform Engineers to understand both the offline and online needs and deliver on those needs
• Research, analyze and select technical approaches for solving difficult and challenging development and integration problems, coach and mentor other engineers in process and methodologies