Amazon Devices Demand Planning team is looking for an Applied Scientist with a background in Operations Research and Management Sciences. We develop sophisticated algorithms that involve learning from large amounts of past data, such as actual sales, prices, promotions, similar products and product’s attributes in order to forecast the demand for all Amazon devices and to use these forecasts to determine if we should green-light products, the level of investment in capital expenditures, ordering material, managing inventory and determining financial performance. We also work closely with Supply Chain and Logistics teams to optimize our inventory allocation in our worldwide channels given operational constraints.
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 share the overall business.
You will have an opportunity to work on large mathematical problems, with large elements of unpredictability. You will write and solve linear and mixed-integer problems to find optimal solutions to build decisions given capacity constraints and the demand distributions. You will also drive process changes that comes with automation and smarter optimization. You are an individual with outstanding analytical abilities, communication skills, and are comfortable working with technical teams and systems. You will be responsible for researching, experimenting, and analyzing forecasting strategies and mathematical models. You will also be prototyping the implementations.
Design and develop complex mathematical, simulation and optimization models and apply them to define strategic and tactical needs and drive the appropriate business and technical solutions in the areas of inventory management, network flow, supply chain optimization, demand planning.
Apply theories of mathematical optimization, including linear programming, combinatorial optimization, integer programming, dynamic programming, network flows and algorithms to design optimal or near optimal solution methodologies to be used by in-house decision support tools and software.
Prototype these models by using modeling languages such as R, MATLAB, Mosel or in software languages such as Python.
Create, enhance, and maintain technical documentation, and present to other Scientists.
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
In order to perform the above responsibilities well, you also need to
Gather data required for analysis and mathematical model building by writing ad-hoc scripts and database queries
Interact with software and multiple business teams across the company to develop an understanding of their business requirements and operational processes.
MS in Operations Research, Industrial Engineering, Management Science or a related field with 6+ years of industry experience
Deep expertise in building mathematical models and prototyping
Deep expertise in stochastic and deterministic optimization techniques and simulation
Track record of designing and building end to end modeling processes and workflows that automate manual processes and that are adopted by large teams
A working knowledge of linear and non-linear optimization methods accompanied by expertise in the use of OR tools (e.g. CPLEX, Gurobi, XPRESS).
Practical experience in implementing optimization models and tools through the use of high-level modeling languages (e.g. AMPL, Mosel, R, MATLAB).
Fluency in a high-level modeling language such as R, SAS, MATLAB or other statistical software, knowledge of relational databases (SQL)
Expert in one or proficient in more than one more major programming languages (C++, Java, Python, etc.)
Strong communication, influencing and partnership skills
Experience building, iterating, and validating predictive data models from scratch
Ability to convey rigorous mathematical concepts and considerations to non-experts
Ability to distill problem definitions, models, and constraints from informal business requirements; and to deal with ambiguity and competing objectives
Superior verbal and written communication skills
PhD in Operations Research, Industrial Engineering or a related field with 6+ years of industry experience
Experience with large data sets, big data and analytics
Prior background in machine learning and forecasting is a plus
Experience designing and supporting large-scale distributed systems in a production environment
Proficiency in at least one modern programming language such as Java or C++/C#
1+ years of relevant development experience in Object-Oriented Design and Service Oriented Architecture