Data Scientist I, Demand Forecasting

Amazon Amazon · Big Tech · Bellevue, WA · Data Science

Data Scientist role focused on demand forecasting within Amazon's supply chain. Responsibilities include developing and supporting data science methodologies, building models for forecasting, bias correction, and contributing to GenAI/LLM research for explainability. The role involves designing and analyzing A/B tests, deriving causal inferences, and communicating insights to stakeholders. The primary artifact is the improved forecast, which directly impacts business decisions like inventory management and labor planning.

What you'd actually do

  1. Design and analyze experiments (A/B tests) to measure the impact of forecast model changes and SCOT initiatives, drawing causal inferences from both experimental and observational data
  2. Develop bias correction models to improve forecast accuracy across Amazon's demand forecasting systems, including National, Regional, Grocery, SSD, Inbound, and CIV forecasts
  3. Contribute to GenAI/LLM-based research for forecast explainability and interpretability, helping stakeholders understand what drives forecast signals
  4. Support and enhance the Labs experimentation platform by building scalable inference and measurement solutions that quantify the impact of forecasting improvements
  5. Work horizontally across the forecasting product portfolio and collaborate with product managers, applied scientists, and engineering teams to embed analytics and ML solutions where they create the most value

Skills

Required

  • Data querying languages (e.g. SQL)
  • Scripting languages (e.g. Python)
  • Statistics
  • Causal inference
  • Experiment design and analysis (A/B testing)
  • Machine learning model development
  • Forecasting techniques
  • Communication skills

Nice to have

  • GenAI/LLM research
  • Bias correction modeling
  • Supply chain optimization

What the JD emphasized

  • bias correction model development
  • GenAI/LLM research for forecast explainability
  • deep analytics for Labs and Foundation Models
  • bias correction models to improve forecast accuracy
  • GenAI/LLM-based approaches for forecast explainability and interpretability
  • Labs experimentation platform
  • design and execute inference and experimentation systems
  • deriving causal inferences using observational and experimental data
  • model variations related to demand prediction, out of stock, seasonality, and different lead times and spans
  • bias correction models to improve forecast accuracy
  • GenAI/LLM-based research for forecast explainability and interpretability
  • Labs experimentation platform
  • building scalable inference and measurement solutions
  • embedding analytics and ML solutions
  • build models addressing ambiguous forecasting questions
  • demand prediction, out of stock, seasonality, and varying lead times and spans
  • translating technical frameworks into business-oriented insights and actionable recommendations
  • exceptional analytics, statistics, judgment, and communication skills
  • extract insights from data and clearly communicate appropriate triggers and actions

Other signals

  • Develop bias correction models to improve forecast accuracy
  • Contribute to GenAI/LLM-based research for forecast explainability
  • Design and analyze experiments (A/B tests) to measure the impact of forecast model changes