Uber - San Francisco, CA
posted about 2 months ago
The ML Foundations team in Uber Eats is engaged in foundational work that significantly impacts various products within the organization. This team is responsible for developing key modeling artifacts that are critical for the business, including entity classifications, entity resolution, attribute enrichments, semantic similarity, complementary recommendation models, and user profiles. By adopting cutting-edge, robust machine learning building blocks, the ML Foundations team plays a vital role in enhancing the capabilities of Uber Eats. The Marketplace Consumer Incentives team is crucial for Uber's profitability and growth, focusing on creating the most efficient incentive structures across all business lines, including Uber Rides and Uber Eats. This team invests heavily in machine learning, causal inference, constrained optimization, and distributed systems to optimize and personalize incentive structures, ultimately increasing consumer engagement. The Shopping Ranking Team aims to enable eaters to make shopping decisions effortlessly and find what they need. This mission is pursued through an ML-driven algorithmic approach, applying state-of-the-art Machine Learning and Optimization techniques to learn from the massive datasets available at Uber, thereby building scalable and reliable shopping intelligence ranking and recommendation systems. The Merchant Pricing team in the delivery marketplace focuses on ensuring optimal merchant selection for consumers. They innovate pricing models that allow merchants to effectively participate in the marketplace, achieving their business objectives with the highest ROI while aligning with Uber's Delivery business goals of driving growth and profitability. In this role, the candidate will build world-class, large-scale incentives ML systems and pioneer an end-to-end user incentives experience. They will innovate and productionize state-of-the-art incentives ML models, customizing them for Uber's specific use cases. Collaboration with cross-functional incentive stakeholders will be essential to drive innovations in user incentive experiences.