Stord is launching Stord Labs, an innovation center designed to evaluate emerging logistics technologies and redefine the future of fulfillment. We are seeking a highly skilled Lead Data Scientist to serve as the primary analytics and modeling expert within our core innovation team.

Unlike most data science roles in logistics that operate far removed from day-to-day operations, this role is embedded directly in a live fulfillment environment. As Lead Data Scientist for Stord Labs, you will build digital twins, develop predictive and prescriptive models, and evaluate agentic AI systems against real-world warehouse workflows inside a dedicated micro-fulfillment facility.

Your work will directly inform how innovations scale across Stord's broader fulfillment network, translating experimental results into enterprise-level operational strategies. You will serve as the technical backbone of a five-person innovation team, partnering closely with controls engineers and operations specialists, and collaborating with frontier AI organizations and academic research partners.

If you bring deep expertise in simulation, machine learning, and applied analytics-and want to work at the intersection of data science and physical operations-this role is designed for you.

What You'll Do:

Digital Twin & Simulation Modeling

• Lead the design and development of digital twin models that accurately replicate end-to-end warehouse operations.
• Ingest and structure operational data from the micro-fulfillment lab to build scalable macro-simulations capable of representing enterprise-scale environments with tens of thousands of SKUs.
• Stress test operational strategies-including slotting algorithms, multi-pass picking, batching logic, and automation workflows-within simulation environments prior to production deployment.

Applied Artificial Intelligence

• Design, test, and deploy AI-driven decision systems directly into operational workflows.
• Develop models for forecasting, labor planning, inventory optimization, task prioritization, and exception handling to improve throughput, speed, and cost efficiency.
• Build lightweight, production-ready analytical tools and algorithms that improve operational performance without heavy infrastructure overhead.

Analytics & Experimentation Validation

• Translate operational data into financial impact models, linking time-and-motion studies to margin improvement, productivity gains, and labor efficiency.
• Partner with operations analysts to design robust experimental frameworks, including success criteria, measurement methodologies, and statistical validation approaches.
• Analyze complex, multi-variable experiments such as inventory commingling strategies and their impact on density, availability, and fulfillment speed.

Academic & Frontier AI Partnerships

• Serve as the primary technical interface with external AI organizations, frontier model providers, and technology partners.
• Collaborate with academic institutions to sponsor applied research in simulation, optimization, and AI-driven operations.
• Integrate external research and capabilities into real-world operational testing within fulfillment workflows.

Basic Qualifications:

• Master's degree or PhD in Data Science, Operations Research, Computer Science, Industrial Engineering, or a highly quantitative field.
• 5+ years of applied data science experience in supply chain, logistics, manufacturing, or other complex operational environments.
• Advanced proficiency in Python, R, and SQL.
• Proven experience building discrete-event simulations, continuous simulations, or digital twin systems using tools such as AnyLogic, Simio, FlexSim, or custom frameworks.
• Strong track record of deploying machine learning and optimization models into live production or operational decision systems.

Bonus Points:

• Experience operating as a standalone data scientist in an R&D lab, innovation center, startup environment, or advanced manufacturing technology setting.
• Familiarity with WMS/OMS data structures and warehouse operational datasets.
• Experience experimenting with large language models (LLMs) or agentic AI systems for workflow automation, exception management, or decision support in operations contexts.