About the job
Join Amazon's Customer Delivery Experience (CDE) Science Team as a Applied Scientist I to improve global logistics through data-driven modeling and analysis. Our team applies advanced machine learning and statistical techniques to enhance delivery experiences for millions of customers worldwide. Working collaboratively with Amazon's logistics operations teams, you will implement proven ML solutions and contribute to continuous improvements across our global fulfillment and delivery network.
Responsibilities
Build and validate predictive models for delivery time estimation using historical delivery data, weather patterns, and traffic information
Implement models to identify delivery exceptions and risk factors using established ML frameworks
Partner with logistics operations teams to understand business requirements and translate them into modeling approaches
Document model methodologies, assumptions, and limitations for team knowledge sharing
Participate in code reviews and contribute to team best practices
Seek feedback from senior team members on proposed solution approaches and methodologies
Qualifications
Minimum
Master's degree in computer science, mathematics, statistics, machine learning or equivalent quantitative field
Experience with any programming language such as Python, Java, C++
Knowledge of one or more ML Frameworks (e.g., PyTorch, TensorFlow) and ML methods including NLP models (BERT, GPT-2/3), computer vision-based models (object detection, image recognition), and text-based models (Seq2Seq, Topic modeling)
Experience in SQL data manipulation
Coursework or project experience in statistical modeling, machine learning, or deep learning
Preferred
Ph.D. in computer science, mathematics, statistics, machine learning or equivalent quantitative field
Experience with AWS data services (e.g., SageMaker, S3, Redshift, EMR)
Experience with distributed computing frameworks (e.g., Spark)
Publications at peer-reviewed ML or AI conferences (e.g., NeurIPS, ICML, KDD)
Experience with deep learning architecture design and model optimization techniques (e.g., pruning, quantization)
Familiarity with A/B testing frameworks and experimentation design
Experience in logistics, supply chain, or operations research domains