About this role
Use advanced machine learning to improve Amazon logistics delivery experiences. Build predictive and classification models for delivery time estimation and delivery exception/risk identification, and partner with logistics operations teams to apply results at scale.
Key Responsibilities
- Build and validate predictive models for delivery time estimation
- Implement classification models to identify delivery exceptions and risk factors
- Apply feature engineering to transportation and logistics data
- Conduct exploratory data analysis to find improvement opportunities
- Create data visualizations and reports and document model methodologies
Technical Overview
Develop supervised learning models using Python or R (pandas, scikit-learn) and strong SQL to extract and transform relational data. Validate and evaluate models with cross-validation and metrics including RMSE, AUC, and precision/recall, supported by statistical testing, and communicate findings through visualizations and reports.
Ideal Candidate
The ideal candidate is an entry-level Data Scientist I with 1+ years of experience building supervised learning models (regression and classification) from problem definition through deployment. They are proficient in Python or R with pandas and scikit-learn, have strong SQL skills, and can evaluate models using cross-validation and metrics like RMSE and AUC while communicating results to non-technical logistics stakeholders.
Must-Have Skills
1+ years of experience building supervised learning models (regressionclassification) from problem definition through deploymentProficiency in Python or R for data manipulation and statistical analysisincluding libraries such as pandasscikit-learnor equivalentStrong SQL skills for data extraction and transformation from relational databasesExperience communicating technical concepts to a non-technical audienceModel evaluation techniques including cross-validationperformance metrics (RMSEAUCprecision/recall)and statistical testingBuild and validate predictive models for delivery time estimationImplement classification models to identify delivery exceptions and risk factors
Nice-to-Have Skills
Experience working with or evaluating AI systems2+ years of experience in data science or machine learning rolesExperience with transportationlogisticsor supply chain optimization problemsFamiliarity with Amazon SageMakerAWS servicesor similar cloud ML platformsExperience with gradient boosting frameworksKnowledge of time-series forecasting or geospatial analysis
Tools & Platforms
PythonRpandasscikit-learnAmazon SageMakerAWS
Required Skills
predictive modelsdelivery time estimationclassification modelsdelivery exceptionsrisk factorsfeature engineeringexploratory data analysisdata visualizationsdata reportingPythonRpandasscikit-learnSQLcross-validationRMSEAUCprecision/recallstatistical testingmachine learningcode reviewstransportation logistics modeling
Hard Skills
predictive modelsdelivery time estimationclassification modelsfeature engineeringexploratory data analysisdata visualizationdata reportingPythonRpandasscikit-learnSQLcross-validationmodel evaluationperformance metricsRMSEAUCprecision/recallstatistical testingmachine learningmachine learning frameworksmodel validationlogistics datatransportation datahistorical delivery dataweather patternstraffic informationdelivery exceptionsrisk factorscode reviewsJira management (not specified in job 3 snippet)
Soft Skills
communication to non-technical audiencecollaborationpartnering with logistics operations teamsdocumenting methodologiesteam best practices participationseeking feedbackownership
Keywords for Your Resume
Data Scientist IData ScientistCustomer Delivery Excellence Sciencedelivery time estimationpredictive modelsclassification modelsdelivery exceptionsrisk factorsfeature engineeringexploratory data analysisdata visualizationslogistics operationsPythonRpandasscikit-learnSQLcross-validationRMSEAUCprecision/recallstatistical testingmachine learningAmazon SageMakerAWSgradient boostingtime-series forecastinggeospatial analysis
Deal Breakers
Bachelor's degree or above in a quantitative field, 1+ years building supervised learning models (regression, classification) from problem definition through deployment, Must have strong SQL skills for data extraction and transformation, Must have model evaluation experience using cross-validation and metrics such as RMSE and AUC
Get matched to jobs like this
Luna finds roles that fit your skills and career goals — no endless scrolling required.
Create a Free Profile