Job Description

We’re building an AI-enabled supply chain that predicts, prescribes, and acts. As a Supply Chain Data Scientist, you’ll develop predictive, prescriptive, optimization, anomaly detection, and simulation models that improve cost, service, and resilience across planning, logistics, and operations.

You will partner with data engineering, AI engineering, and business stakeholders to translate problems into deployable solutions-delivering decision signals that are embedded into operational workflows, planning systems, and agentic experiences.

Responsibilities include but not limited to:

• Build predictive models for key supply chain processes using statistical, machine learning, and deep learning techniques
• Develop prescriptive analytics and optimization models to recommend optimal actions under real-world constraints
• Quantify tradeoffs between cost, service, capacity, and risk
• Detect variability, disruptions, and anomalies across supply chain operations
• Build simulations and scenario models to support strategic and operational decisions
• Partner with stakeholders to translate business problems into data science solutions
• Enable AI and agentic workflows by producing high-quality predictive and prescriptive signals
• Merge and analyze large, complex datasets to discover trends, patterns, and actionable insights

Qualifications

Basic Qualifications:

• Master’s degree in data science, statistics, computer science or related field
• 8+ years of professional experience, including 2+ years in supply chain analytics (planning, forecasting, logistics, manufacturing, or operations)
• Strong proficiency in Python and SQL
• Proven experience with predictive modeling (statistical, ML, deep learning), optimization techniques (LP, MIP, constraint programming), and simulation techniques (Monte Carlo, discrete event)
• Knowledge of advanced statistical techniques and concepts (regression, distributions, statistical tests)
• Familiarity with a variety of machine learning techniques (clustering, decision trees, neural networks) and their real-world advantages and limitations
• Experience with data manipulation libraries such as pandas and NumPy
• Experience with ML frameworks such as scikit-learn, XGBoost, PyTorch, or TensorFlow
• Knowledge of big data frameworks and platforms such as Spark, Databricks, or Snowflake

Preferred Qualifications:

• PhD
• Experience with supply chain planning, forecasting, or logistics datasets
• Experience with Databricks, Spark, Snowflake or Palantir Foundry & AIP
• Experience with MLOps practices (model monitoring, CI/CD for ML)