Pipeline: AI/ML Supply Chain Data Scientist

BlockTXM•Columbus, OH

About The Position

A Supply Chain Data Scientist applies machine learning and advanced analytics to solve complex supply chain problems. This role, often full -time in larger companies or consulting for specific projects, leverages data to forecast demand, optimize routes and inventory, and improve overall network efficiency. With the rise of AI in logistics, Ohio firms (retailers, manufacturers) are seeking talent who can turn big data (from sales, production, IoT sensors) into predictive insights and competitive advantage.

Requirements

Data Science
Machine Learning
Python (Pandas/Scikit -learn)
R
Predictive Analytics
Forecasting
Optimization
SQL
Big Data (Hadoop/Spark)
Statistics
Supply Chain Modeling
Linear Programming
Time -Series Analysis
TensorFlow/PyTorch (if deep learning)
Data Visualization
Operations Research
Algorithm Development
Cloud ML (AWS SageMaker/Azure ML)
Data Cleaning
IoT Data
Demand Planning
Logistics Optimization
Problem Solving
Business Communication
Cross -Functional Collaboration
Domain Knowledge (Supply Chain)

Responsibilities

Analyze large datasets of supply chain information (e.g., historical sales, inventory levels, shipment transit times) to identify patterns, trends, and outliersaffecting performance.
Develop and refine forecasting modelsfor demand planning, lead times, or supply, using techniques like time -series analysis or machine learning regression to improve accuracy over traditional methods.
Design and implement optimization algorithms (operations research or AI -based) for routing, network design, inventory placement, and resource allocation that minimize cost or maximize service level.
Use predictive analytics to anticipate issues such as delays, stockouts, or quality problems – e.g., predicting which shipments might arrive late or which SKUs are at risk of going out -of -stock.
Collaborate with cross -functional teams (logistics, production, procurement) to ensure models and analytics align with operational realities and constraints. (For example, incorporate warehouse capacity or carrier schedules into optimization models.)
Build data pipelines and tools(with help of data engineers) to gather data from various sources (ERP, WMS, IoT sensors, external market data) and preprocess it for analysis (cleaning, feature engineering).
Develop dashboards or applications to deliver the insights to stakeholders in real -time – for example, a control tower view that uses machine learning outputs to flag anomalies or recommend actions.
Validate and back -test models; measure the accuracy and business impact of data science initiatives (e.g., how much inventory reduction was achieved or how much service level improved due to the model).
Present findings and complex analyses in a clear, concise manner to non -technical stakeholders, translating data science results into business recommendations (e.g., “reducing safety stock by 10% in these warehouses based on our model’s insights”).
Stay current on AI/ML trends and tools (like advanced neural networks for demand sensing, or reinforcement learning for dynamic routing) and experiment with their applicability to supply chain challenges.
Support broader digital transformation efforts, possibly guiding junior analysts or influencing IT on infrastructure needed (cloud computing, big data platforms) for advanced analytics.