Data Scientist – Transportation & Logistics Intelligence

About ShipMonk

ShipMonk isn't just a 3PL; we're a growth partner for merchants. We provide cutting-edge technology and a network of owned and operated fulfillment centers that empower high-growth ecommerce and DTC brands to stress less and grow more. With over 2,500 employees across five countries, we're on a mission to revolutionize fulfillment by providing everything from the fastest click-to-delivery and real-time inventory to custom solutions—all with a merchant-first mindset.

Why ShipMonk?

We believe in building for the long term, and our success is powered by five key differentiators that help us become true partners to our merchants.

● Global Fulfillment Network: Our 12+ owned and operated fulfillment centers span the US, Canada, Mexico, the U.K., and Mainland Europe. We never outsource, ensuring quality and consistency.
● Proprietary Technology: We've eliminated the need for tribal knowledge with our AI-powered platform. It provides a real-time, unified view of inventory and orders, giving our merchants the control and visibility they need to succeed.
● Unrivaled Support: We provide hands-on, "mom and pop" support with a global reach. Our dedicated teams are on-site at every fulfillment center, ready to jump into action.
● Transparent Pricing: We believe in honest, long-term partnerships. Our all- inclusive pricing means predictable costs, with no hidden fees or surprises.
● Committed to the Future: We invest over $10 million annually in research and development to ensure our technology and services continually evolve, helping merchants plant roots with a partner who is here to stay.

Data Scientist – Transportation & Logistics Intelligence

About the Role:

ShipMonk has built world-class infrastructure for shipping—our Virtual Carrier Network (VCN), claims systems, and logistics modeling are the rails. Now, we need the engine. We are seeking a Data Scientist – Transportation & Logistics Intelligence to transform our transportation systems to "predictive-first."

In this role, you won’t just be "analyzing data"—you’ll be building the autonomous logic that powers millions of shipments. You are the architect who will replace manual "if/then" rules with real-time, high-margin predictive models. Your mission is to bridge the gap between logistics physics and machine learning, ensuring that manual becomes modeled and reactive becomes predictive.

Desired Experience:

• Education: Master’s or PhD in Data Science, Statistics, Operations Research, or a related quantitative field (or equivalent practical experience).
• Data Core: 4+ years of experience building and deploying predictive models into production environments.
• Data Engineering: Strong proficiency with dbt and SQL within a Snowflake (or BigQuery/Redshift) environment. You should be comfortable collaborating on complex DAGs and version-controlled data pipelines.
• Logistics DNA: Previous experience in transportation, supply chain, or e-commerce logistics is a massive plus. You should understand the nuances of carrier performance, transit latencies, and "last-mile" variables.
• The Stack: Expert-level proficiency in Python and SQL. Experience with machine learning frameworks (e.g., Scikit-learn, XGBoost, PyTorch) and cloud-based data warehouses (Snowflake, BigQuery).
• Business Acumen: Ability to translate complex model outputs into "Margin impact" or "Conversion growth" for stakeholders.

Skills & Responsibilities:

• VCN Optimization (The Margin Engine): Build real-time risk/value models. You’ll build the logic that weighs package value vs. risk of loss to ensure we never overspend on "safe" routes or under-insure "risky" ones.
• Precision EDD (The Conversion Driver): You will develop dynamic Estimated Delivery Date (EDD) models that adjust in real-time based on live network health, weather, and historical carrier latency.
• Predictive "At-Risk" Intelligence: Build the "early warning system" for our warehouse and support teams. You’ll develop models that identify "lost" or delayed packages before a merchant or customer even notices—enabling proactive resolution and automated claims.
• Collaborative Data Preparation: Partner with Engineering to co-author and refine the dbt models and SQL transformations that power your work. You’ll ensure the "preparation layer" is optimized for feature engineering and model training.
• Scalable Modeling: Transform manual logistics workflows into autonomous systems. You’ll be responsible for ensuring our intelligence scales with our global warehouse footprint.
• Cross-functional Collaboration: Partner with Product Managers and Engineering teams to integrate your models directly into the ShipMonk application, moving from "insights on a slide" to "logic in the code."
• A/B Testing & Validation: Design and execute experiments to validate that your models are actually driving the expected increases in margin and delivery reliability.

ShipMonk is an equal opportunity employer. We value diversity and do not discriminate on the basis of race, religion, color, national origin, gender, sexual orientation, age, marital status, veteran status, or disability status.