Staff Machine Learning Engineer, Fulfillment Planning
San Francisco, CA; Sunnyvale, CA·$204K–299K
Machine Learning · Optimization
About the Team
The Fulfillment Planning team builds the intelligence that powers DoorDash’s logistics network. We optimize how deliveries are planned and executed across the full delivery lifecycle, improving customer experience, merchant outcomes, Dasher efficiency, and DoorDash profitability. Our mission is to improve fulfillment quality while reducing fulfillment cost. We do this by applying machine learning, optimization, and systems engineering to the core decisions behind assignment, routing, batching, timing, and fulfillment estimation.
The team works on some of DoorDash’s most important logistics systems, including:
- The core assignment engine that matches deliveries with Dashers in real time.
- Real-time ETA and fulfillment estimation systems for consumers, Dashers, and merchants across diverse geographies and all business lines.
- Assignment and planning algorithms for specialized delivery types, including grocery, retail, parcel, and catering.
- ML models and optimization algorithms that shape demand, improve service quality, and reduce cost.
- Tier-0 logistics services that require high reliability, low latency, and strong operational discipline.
The team also builds reusable ML systems and modeling patterns that scale across DoorDash’s logistics ecosystem. This role will help define the technical direction and best practices for logistics ML at DoorDash.
About the Role
We’re looking for a Staff Machine Learning Engineer to lead the design, development, and deployment of large-scale production ML systems that drive real-time decisioning across DoorDash’s