Data Scientist, AMZL Strategic Planning- Analytics Automation

Job summary
Amazon Logistics Strategic Planning team is seeking an experienced Data Scientist, to lead the science development of algorithmic tools, supporting long-term AMZL Strategic Planning.

You are an outstanding Data Scientist with a background in Operations Research, have passion for technology, complex data sets but not tool-centric. You determine what technology works best for the problem at hand and apply it accordingly. You can explain complex concepts to your non-technical customers in simple terms.

You are uncompromisingly detail oriented, smart, efficient, and driven to help our business succeed. You develop sophisticated algorithms that involve learning from large amounts of data, designing solutions to resolve long-term Logistics Network Topology design constraints, capacity constraints and improve demand distributions for the complex Last Mile Logistics network

Key job responsibilities
In this role, you will work individually and with other Research scientists, data scientists, BIEs and DEs in the team. You develop your own scientific approaches and partner with teams as they deploy algorithmic solutions to our stakeholders. You will also partner with business leaders on projects that evaluate long-term strategic AMZL network choices, and present strategy papers to our senior-most leaders to drive long-term impact.

To accomplish this, we expect you to have a strong research background in at least one of the following disciplines: operations research, computer science, operations management, statistics, or applied mathematics. You should have business domain knowledge in logistics management with some knowledge of inventory management theory and practice.

A day in the life
• Design, develop complex mathematical simulations, optimization models and apply them to define strategic and tactical needs. Drive the appropriate business and technical solutions in the areas of Topology Network Design and Capacity Engineering
• Apply theories of mathematical optimization, including linear programming, combinatorial optimization, integer programming, dynamic programming, network flows and algorithms to design optimal solutions to be used by in-house decision support tools
• Prototype these models by using modeling languages such as Python, R, Scala. Maintain technical documentation; present your design ideas to other Scientists, Data Engineering teams
• Plan projects from a scientific perspective, managing product features, technical risks, milestones and launch expectations
• Go above and beyond supporting organization roadmap with quantifiable data; onboard new technologies onto Science team's toolbox

About the team
AMZL Strategic Planning- Analytics Automation team focuses on long-term (3 –7 years) planning with high cost decisions. There are various strategic questions team is attempting to solve, such as: what is the optimal Topology Design given the location/site availability constraints? How can we predict accurately fulfillment pattern for different customer clusters at new locations? What techniques can evaluate, new site/facility recommendation for long term growth? We predict network utilization improvements over the horizon, with simulation of how our choices will perform. We bring all these analytics as guidance/ recommendation, for multi-year planning and support execution.

Basic Qualifications

• MS in Operations Research, Industrial Engineering, Management Science, Computer Science
• 5 years of professional experience in industry with Optimization Research
• Strong coding and problem-solving skills in at least one programming language such as Python, Java, SQL, Scala, etc.
• Familiar with AWS environment, Data pipeline-ETL setups, such as S3, Sage Maker, Athena, Glue and other automation methods
• Sound theoretical understanding of broad concepts, and demonstrable expertise in application of: regression, classification, deep learning, clustering
• Ability to distill informal customer requirements into problem definitions and quantify improvements in value

Preferred Qualifications

• Experience with fully automated training (e.g. automatic re-training, automatic testing) on techniques such as Random Forest, Regression (Linear), Time-Series (ARIMA) and Neural network (LSTM, CNN) using large datasets
• Experience writing production-quality code using collaborative process such as Git and AWS. Fine tuning and designing complex mathematical problem into various decomposition algorithm.


Amazon is committed to a diverse and inclusive workplace. Amazon is an equal opportunity employer and does not discriminate on the basis of race, national origin, gender, gender identity, sexual orientation, protected veteran status, disability, age, or other legally protected status. For individuals with disabilities who would like to request an accommodation, please visit https://www.amazon.jobs/en/disability/us.