Data Science Solutions Lead

Data Science Solutions

Lead

Location : Plano, TX (Onsite)

Start date : ASAP

End Date : 3/31/2027

Bill Rate : Competitive Market Rate on W2 only (no 1099 or C2C allowed)

Visa : No restrictions

Job Summary:

US based technical and Data Science lead for the Warehouse Optimization program, serving as the central bridge between Product, Warehouse Operations, Data Science, Data Engineering, and application teams.

The role will translate warehouse business challenges and product vision into optimization problems, Data Science requirements, solution architecture, and actionable technical direction for globally distributed teams.

Key Responsibilities

• Serve as the primary & single technical and Data Science point of contact, connecting Product Owners, Warehouse Managers, business stakeholders, and application delivery teams.
• Partner with Warehouse Managers and Product teams to understand slotting challenges, operational constraints, business rules, and expected outcomes.
• Translate business objectives into optimization problems including objective functions, decision variables, constraints, KPIs, and acceptance criteria.
• Define and communicate the end-to-end solution vision covering data readiness, optimization models, simulation, recommendation workflows, operational integration, and impact measurement.
• Translate US stakeholder discussions into clear Data Science requirements and technical direction for offshore Data Scientists and Engineers.
• Lead data-readiness and feasibility assessments for PDC rollout and identify gaps that could materially affect optimization quality.
• Define simulation/whatif approaches and methodologies to compare projected versus realized benefits such as walking-distance reduction, productivity, and labor efficiency.
• Facilitate technical workshops and communicate complex optimization concepts clearly to business, Product, and warehouse stakeholders.
• Provide technical leadership for warehouse optimization approaches including Popularity, COI (Cubeper-Order Index), demand-based optimization, affinity/co-pick analysis, and space/capacity constraints.
• Lead the design of Affinity Optimization and guide how frequently copicked/ordered parts are translated into practical slotting recommendations.
• Guide and review feature engineering, model assumptions, optimization methodology, constraints, validation, scenario analysis, and model performance.
• Define required datasets and dataquality expectations across WMS, part/location masters, order and pick history, demand/forecast data, and warehouse layout information.
• Validate recommendations with Warehouse Managers for operational feasibility, including capacity, travel paths, replenishment, handling, and local warehouse rules.
• Ensure the solution is reusable, configurable, and scalable across multiple PDCs, rather than becoming facility specific implementations.

Primary Technology Stack

Languages: Python, PySpark, SQL

Data Platform: AWS S3, Amazon Redshift, AWS Glue

Streaming / Integration: Kafka

Source Systems: DB2, WMS, TBDP, P360, EPC

Graph / Modeling: Knowledge Graph / graph datasets

Orchestration: Airflow or AWS Step Functions

DevOps: Git, CI/CD

Must Have Skills:

Ability to convert ambiguous operational problems into structured analytical/optimization problems with measurable outcomes.

Strong Python and SQL skills with the ability to review algorithms, model logic, and analytical outputs.

Experience designing endto-end optimization solutions, from source data through recommendations and operational consumption.

Strong clientfacing consulting skills including structured problem solving, stakeholder management, workshop facilitation, and executive communication.

Experience leading onshore/offshore Data Science and Engineering teams and converting stakeholder vision into executable technical work.

Data Science depth sufficient to technically lead and challenge Data Scientists, rather than only coordinate delivery.

10 plus years of experience across Data Science, Operations Research, Supply Chain Technology, Analytics, or Solution Architecture, with strong technical leadership.

Strong Operations Research knowledge, including objective function formulation, constraints, trade-offs, and mathematical optimization.

Strong handson experience building ETL/ELT pipelines in Python and SQL.

Strong experience in warehouse optimization, slotting, inventory placement, fulfillment, or distribution center operations.

Understanding of slotting approaches including Popularity/ABC, COI, demand-based slotting, affinity/co-pick analysis, and capacity optimization.

Good-To-Have Skills

• Experience with graph data models or knowledge graphs Experience scaling optimization solutions across multiple warehouses/PDCs/DCs.
• Warehouse simulation, digital twins, or whatif scenario modeling.
• Graph algorithms, shortestpath/travel-distance modeling, and warehouse topology.
• Forecasting/seasonality applied to dynamic slotting strategies.
• Cloud data platforms such as AWS and Databricks and enterprise WMS integration.
• Model governance, explainability, monitoring, and projectedvs-realized benefit measurement.
• Automotive parts distribution, aftermarket/serviceparts, or large-scale supply-chain experience.
• Master’s degree in Operations Research, Industrial Engineering, Data Science, Computer Science, Supply Chain Analytics, or a related quantitative discipline.

Note

Function Data Science / Solution Architecture

Location: USA, Based out of Dallas