The Amazon Last Mile Flex Delivery Planning Science team is looking for an L5-L6 Research Scientist or Applied Scientist with strong skills in Optimization/Operations Research. Flex is Amazon's gig economy platform for procuring drivers to satisfy the overflow demand from AMZL, as well as specialty deliveries like Sub-same Day Deliveries (SSD) and groceries (GSF). Like Uber, drivers download the Flex app and click on offers of work time blocks, during which they are paid to execute deliveries from a particular warehouse, over a particular time window. Unlike Uber, we allow drivers to schedule work up to a week in advance. Challenges involve scheduling drivers over time, in the presence of long lead-times, uncertainties in both demand and supply, while minimizing cost and the risks of late deliveries or excess drivers. We are also working on the integration of our driver scheduling systems with capacity planning, routing & assignment, dynamic pricing, smart offer targeting, and long-term value. We are looking for candidates with strong skills in Optimization modeling (Mixed Integer Programming, Dynamic Programming, Decomposition Methods), as well as solid skills in Python coding and data collection and analysis. Some background in Control Theory, Machine Learning, and Economics would be helpful too.
The successful candidate will be a self-starter, comfortable with ambiguity, with strong attention to detail, an ability to work in a fast-paced and ever-changing environment and a desire to help shape the overall business.
Key job responsibilities
Design and develop advanced mathematical, optimization models and apply them to define strategic and tactical needs and drive the appropriate business and technical solutions in the areas of Delivery Planning, supply chain optimization, network optimization, economics, and control theory.
Apply mathematical optimization and control techniques (linear, quadratic, SOCP, robust, stochastic, dynamic, mixed-integer programming, network flows, nonlinear, nonconvex programming, decomposition methods, model predictive control) and algorithms to design optimal or near optimal solution methodologies to be used by in-house decision support tools and software.
Research, prototype, simulate, and experiment with these models by using modeling languages such as Python, MATLAB, Mosel or R; participate in the production level deployment.
Create, enhance, and maintain technical documentation
Present to other Scientists, Product, and Software Engineering teams, as well as Stakeholders.
Lead project plans from a scientific perspective by managing product features, technical risks, milestones and launch plans.
Influence organization's long-term roadmap and resourcing, onboard new technologies onto Science team's toolbox, mentor
other Scientists.
We are open to hiring candidates to work out of one of the following locations:
Bellevue, WA, USA