Applied Science Manager

Job ID: 1362703 | Amazon.com Services LLC

DESCRIPTION

How can we use optimization techniques and Machine Learning (ML) to build algorithms to better resolve our Selling Partners issues? How can we optimally route phone, email and chat contacts form Selling Partners to improve our Associates occupancy rates? How can we optimize day-to-day staffing and scheduling in Amazon service centers by leveraging intra-day data on multiple key planning inputs (for example average handle time)? How to leverage ML recommendations to route incoming contacts to the most optimally skilled associates to quickly and successfully resolve the issues that Selling Partners are experiencing, resulting in quicker and successful resolution of the issues sellers experiencing?

The answers to these questions and others like them are core to helping Amazon’s Marketplace business thrive and expand, including delivering best-in-the-class experience for our Selling Partners and call center Associates. Our cross-functional team works closely with various stakeholders world-wide such as Finance, Operations, Regional Capacity Planners, Global Planning, Hiring and Training to help them with data-driven business decisions.

Using AWS’ large-scale computing resources the Applied Science Manager will develop and deploy optimization algorithms and ML models to match demand (incoming contacts from selling partners) and supply (daily schedules for call center associates) to improve the service levels. The Applied Science Manager will work with domain experts and engineers to help put those algorithms into production and continuously improve their performance. The Applied Science leader will interact with the Amazon ML/Optimization community and mentor Scientists and Software Development Engineers with a strong interest in optimization. Your work will directly benefit sellers, vendors, brands and associates on the Amazon Marketplace platform. We are looking for a passionate, hard-working, and talented Applied Science Manager who has experience leading science teams in a fast-paced matrixed organization to build mission critical, agile and scalable big-data solutions that deliver high-impact results

BASIC QUALIFICATIONS

MS in Operations Research, Mathematics, Statistics, Computer Science, Engineering, Physics or a related quantitative field.
· 4+ years of hands-on experience in developing, deploying, iterating and validating optimization algorithms.
· Apply theories of mathematical optimization, including Linear Programming (LP), Combinatorial Optimization, Integer Programming (IP), Dynamic Programming (DP), Nonlinear Programming (NLP), network flows and algorithms to design optimal or near optimal solution methodologies to be integrated with internal platforms/tools.
· Expert knowledge of solution methods for Linear Programming (e.g., simplex) and Integer Programming (branch and bound, Lagrangian relaxation), decomposition techniques, interior point methods and heuristic optimization.
· Strong algorithm development experience in developing, testing, and deploying to production.
· Proficient in programming languages such as Python, C/C++ and Java.
· At least 2 years of experience in designing and building scalable technical solutions using cloud computing platforms (e.g. AWS, Azure, Google Cloud).
·At least 2 years of experience in managing a team of scientists (applied scientist/research scientist) and engineers.
· Excellent oral and written communication skills, with the ability to communicate complex technical concepts and solutions to all levels of the organization.

PREFERRED QUALIFICATIONS

The ideal candidate will have a PhD in Operations Research, Mathematics, Statistics, Computer Science, Engineering, Physics or a related quantitative field, and 6+ years of relevant work experience, including:
· Experience applying theoretical models in an applied environment.
· Hands-on experience with optimization packages and solvers such as FICO XPRESS, MOSEL, CPLEX and Gurobi.
· Practical experience in implementing optimization algorithms on large datasets.
· Experience with discrete event simulation with stochastic inputs.
· Expertise in various queuing and scheduling algorithms.
· Experience in machine learning and forecasting.
· Strong personal interest in learning, researching, and creating new technologies with high commercial impact.
· Significant peer reviewed scientific contributions in relevant field.
. At least 4 years of experience in managing a team of scientists (applied scientist/research scientist) and engineers.
. At least 4 years of experience in designing and building scalable technical solutions using cloud computing platforms (AWS).