Role overview
Earners (drivers and couriers) are an integral part of Uber's multi-sided marketplace. They provide the time and the means to move people and things. Importantly, they enable the connection between the physical and digital world to make the movement happen at the push of a button for everyone, everywhere.
Within Uber, Earner Growth plays a critical role in earners' journey as the team is responsible for earner onboarding, activation, early life cycle, and resurrection. This presents the teams with the opportunity to shape and tailor the product experience during earners' many firsts (i.e., first time interacting on the Uber platform, choosing the earning opportunity, going online, receiving incentive offers, completing a trip, or reading the earnings summary). These firsts can be daunting.
Therefore, making sure that the earner journey is great at every touch point is important to build trust with Earners, communicate Uber's value proposition, and ensure each firsts to be a great experience.
What you'll work on
- Build statistical, optimization, and machine learning models
- Develop innovative new earner incentives that earners for choosing our network and optimizing Uber's new earner incentives spend
- Optimize Uber's background check spend and onboarding funnel
- Design recommendation engines to recommend the most relevant earning opportunities and early lifecycle content
- Develop matching algorithms for driver to driver mentorship program
- Model and predict earner behaviors to improve earner experience throughout the onboarding funnel
- The team employs a variety of ML/AI techniques, spanning from causal ML meta learners, supervised ML, RL multi-armed bandits, genAI LLM to deep learning embeddings to build impactful data products.
- Work closely with multi-functional leads to develop technical vision, new methodological approaches, and drive team direction. Collaborate with cross-functional teams such as product, engineering, operations, and marketing to drive ML system development end-to-end from conceptualization to final product.
What we're looking for
- 8+ years of industry experience in machine learning, including building and deploying ML models.
- Publications at industry recognized ML conferences.
- Experience in modern deep learning architectures and probabilistic modeling.
- Experience with optimization techniques, including reinforcement learning (RL), Bayesian methods, causal ML meta learners, genAI LLM.
- Expertise in the design and architecture of ML systems and workflows.