Sr Machine Learning Engineer

The Deliverability team sits at the core of Uber’s delivery marketplace as part of Merchant Optimization. Serving as the critical gating layer for every Uber Eats transaction, our systems answer the fundamental real-time question: "Can this merchant deliver to this eater right now?" 
 

We optimize merchant delivery zones to maximize platform selection while balancing marketplace reliability, timeliness, and profitability. The decision made by the deliverability services directly shape selection breadth and business metrics across key downstream platforms, including Search, Feed, and Ads.

Role & Responsibilities

As a Senior Machine Learning Engineer on the Deliverability team, you will drive the technical vision, end-to-end design, and productionization of core ML systems powering global delivery marketplace decisions. Specifically, you will:

• Product & Domain ML Architecture: Architect and translate complex marketplace challenges into high-throughput, large scale ML solutions for delivery zone optimization.
• Design & Train Core Models: Develop, evaluate, and continuously refine state-of-the-art machine learning models that dynamically optimize merchant delivery coverage, balancing conversion, order volume, and fulfillment efficiency.
• Production Pipelines & ML Infrastructure: Engineer, deploy, and operate scalable ML inference pipelines, feature stores, model serving infrastructure, and automated retraining workflows handling high-throughput global delivery evaluations.
• Marketplace Optimization & Experimentation: Lead data-driven investigations to diagnose marketplace inefficiencies, execute online A/B testing and leverage telemetry to drive core business metrics.
• Cross-Functional Technical Leadership: Partner closely with Product Management, Data Science, Operations, and Core Infrastructure teams to align technical roadmaps and define cross-platform ML standards.

• 5+ years of hands-on professional experience designing, training, and operating production ML models at scale.
• Proactive and strong analytical mindset with a passion for uncovering insights from complex data distributions to drive technical decision-making and project buy-in.
• Advanced proficiency in Python and mainstream machine learning frameworks (e.g., PyTorch, TensorFlow, Scikit-learn).
• Solid theoretical foundation in classic and modern ML algorithms, including and not limited to gradient-boosted trees (XGBoost, LightGBM), deep neural networks, and statistical modeling.
• Proven record of taking complex ML systems end-to-end from initial problem formulation and offline validation to large-scale production deployment.
• Practical experience developing automated feature engineering pipelines, using feature store technologies, model monitoring platforms, and executing controlled online A/B testing in production.

• PhD candidate 3+ years of industry experience
• Experience with geospatial libraries (e.g., H3, S2 Cell).
• Experience with Graph Neural Networks (GNNs), and/or deep learning recommendation systems.
• Demonstrated ability to drive cross-functional technical initiatives, mentor junior engineers, and deliver complex multi-phase engineering projects.
• Familiarity with distributed data processing systems (e.g., Spark, Ray, Flink) and foundational concepts in two-sided marketplace optimization.

For San Francisco, CA-based roles: The base salary range for this role is USD $202,000 per year - USD $224,000 per year.

For Sunnyvale, CA-based roles: The base salary range for this role is USD $202,000 per year - USD $224,000 per year.

For all US locations, you will be eligible to participate in Uber's bonus program, and may be offered an equity award & other types of comp. All full-time employees are eligible to participate in a 401(k) plan. You will also be eligible for various benefits.

Ready to Ride?