Expedia

Overview

The Meta/SEM Bidding Programs team at Expedia Group is looking for a Machine Learning Engineer III who mentors junior engineers, applies modern data and ML engineering principles to improve existing systems, and leads complex, well-defined projects in a high-scale production environment.

About Expedia

Expedia Group includes three flagship consumer brands - Expedia, Hotels.com, and Vrbo - along with a leading B2B travel business and travel advertising offerings. Across our brands and business, we help travelers explore the world with confidence and ease.

Requirements & Eligibility

• 5+ years of relevant professional experience with end-to-end machine learning engineering pipelines in production
• Bachelor’s or Master’s degree in a technical field (e.g., Computer Science) or equivalent relevant work experience
• Strong command of Spark (or similar big data frameworks)
• Proficiency with ML libraries such as PyTorch and/or TensorFlow
• Solid ML fundamentals with working knowledge of deep learning and big data concepts
• Hands-on experience evaluating and monitoring ML models in production

Key Responsibilities

• Collaborate with peers and stakeholders across the organization to understand cross-dependencies, shape solutions, and translate experimental DS workflows into robust production pipelines.
• Develop, refactor, and test complex ML and software components, applying solid software engineering practices to produce clean, maintainable, and optimized code.
• Contribute to the design of big data and ML applications, including how models are trained, evaluated, and served at scale across batch and streaming inference workflows.
• Evaluate, monitor, and operate ML models in production, instrumenting pipelines to capture online and offline metrics and using them to drive iteration.
• Diagnose model and pipeline issues and drive mitigations such as retraining, recalibration, and feature or architecture changes.
• Design and implement guardrails for production models to protect customer and business outcomes and improve reliability.