Machine Learning Engineer

About the role and team 

Engineering at Uber means building high-impact, scalable machine learning solutions under real-world constraints. As a Machine Learning Engineer II on the Rider ML team, you will design, deploy, and optimize production ranking, candidate retrieval, and recommendation systems that power core experiences for millions of riders globally. You will solve complex personalization, real-time inference latency, feature store integration, and large-scale streaming data challenges using state-of-the-art ML modeling architectures (such as deep neural networks, multi-task learning, and GBDT models). We are looking for engineers who excel at system architecture, maintain rigorous feature quality and online model drift monitoring, and thrive on cross-functional collaboration with Data Science, Product, and Platform teams to turn high-throughput data streams into predictive models that move the physical world.

What you’ll do 

• Design, develop, and maintain high-quality machine learning models and code for personalization, candidate generation, multi-objective ranking, and recommendation features of moderate complexity.
• Build and scale foundational ML infrastructure, automated model retraining pipelines, and near-real-time streaming feature pipelines (e.g., Flink, Kafka), balancing technical debt while maximizing model AUC, NDCG, and downstream business metrics.
• Own the ML software lifecycle end-to-end, from drafting design docs and setting up feature extraction/transformation pipelines to monitoring real-time inference latency (p95/p99 SLAs) and resolving production model incidents.
• Collaborate across disciplines - including Product, Data Science, and Ops - to translate ambiguous product requirements into scalable ML system architectures.
• Champion ML engineering best practices by conducting rigorous code and model architecture reviews, establishing offline validation (backtesting, cross-validation) and online A/B testing frameworks, and optimizing model inference throughput.
• Navigate internal complexity and stakeholder inquiries to unblock dependencies, maintain rigorous feature drift, label leakage, and model performance tracking, ensuring high reliability in production decisioning systems.

Basic Qualifications 

• 2+ years of professional software engineering experience in machine learning.
• Hands-on experience with modern deep learning and ML frameworks (e.g., PyTorch, TensorFlow) and a strong foundation in feature engineering, loss function design, hyperparameter optimization, and offline evaluation metrics.
• Strong proficiency in Python and one or more object-oriented or functional languages (e.g., Go, Java, C++).
• Bachelor’s or Master’s Degree (or equivalent experience) in Computer Science, Machine Learning, Data Science, or a related technical field.
• Demonstrated track record of writing unit/integration tests, verifying model functionality, and implementing basic monitoring for system stability.

Preferred Qualifications 

• Demonstrated experience designing, deploying, and maintaining production recommendation, ranking, or personalization systems.
• Hands-on expertise with central feature stores (e.g., Palette), embeddings, and real-time or near-real-time (NRT) feature engineering pipelines.
• Experience establishing robust model monitoring, feature quality tracking (detecting skew/drift), and automated offline evaluation paired with online A/B experimentation systems.
• Proficiency with Big Data frameworks (e.g., Spark, Flink), distributed training, and real-time streaming infrastructure (e.g., Kafka) for distributed, large-scale ML systems.